Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 462 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0963. Min Range: -7.0963
Max Act: 7.0963. Min Act: -0.1700
Data Index: 702697 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.9400. Min Act: -0.1700
Data Index: 4263717 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.7213. Min Act: -0.1700
Data Index: 5045536 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.5963. Min Act: -0.1700
Data Index: 45329 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.5650. Min Act: -0.1700
Data Index: 7023671 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.5025. Min Act: -0.1700
Data Index: 325040 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.5025. Min Act: -0.1700
Data Index: 7841312 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.5025. Min Act: -0.1700
Data Index: 3813903 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.4713. Min Act: -0.1700
Data Index: 6785989 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.4400. Min Act: -0.1700
Data Index: 5054554 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.4088. Min Act: -0.1700
Data Index: 5493730 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.4088. Min Act: -0.1700
Data Index: 5054555 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.3775. Min Act: -0.1700
Data Index: 8663782 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.3775. Min Act: -0.1700
Data Index: 2319359 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.3775. Min Act: -0.1700
Data Index: 936835 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.3463. Min Act: -0.1700
Data Index: 2161990 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.3150. Min Act: -0.1700
Data Index: 3414806 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.3463. Min Act: -0.1700
Data Index: 3813904 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.3463. Min Act: -0.1700
Data Index: 5958189 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0963. Min Range: -7.0963
Max Act: 6.3463. Min Act: -0.1700
Data Index: 1028423 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19