Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.9410. Min Range: -11.9410
Max Act: 11.9410. Min Act: -0.1700
Data Index: 482904 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9410. Min Range: -11.9410
Max Act: 11.2535. Min Act: -0.1700
Data Index: 8061833 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.6910. Min Act: -0.1700
Data Index: 8146665 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.6285. Min Act: -0.1700
Data Index: 996571 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.4410. Min Act: -0.1700
Data Index: 4479339 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.4410. Min Act: -0.1700
Data Index: 5304997 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.5035. Min Act: -0.1700
Data Index: 7993928 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.3785. Min Act: -0.1700
Data Index: 3342305 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.3785. Min Act: -0.1700
Data Index: 33075 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.3160. Min Act: -0.1700
Data Index: 2797711 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.2535. Min Act: -0.1700
Data Index: 886381 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.2535. Min Act: -0.1700
Data Index: 7837575 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.2535. Min Act: -0.1700
Data Index: 33073 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.1910. Min Act: -0.1700
Data Index: 5818946 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.1910. Min Act: -0.1700
Data Index: 1297671 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.1910. Min Act: -0.1700
Data Index: 3472372 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.2535. Min Act: -0.1700
Data Index: 829984 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.1910. Min Act: -0.1700
Data Index: 2831472 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.1285. Min Act: -0.1700
Data Index: 7169531 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9410. Min Range: -11.9410
Max Act: 10.1285. Min Act: -0.1700
Data Index: 5102788 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19