Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3908 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5765. Min Act: -0.1700
Data Index: 4948118 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5608. Min Act: -0.1700
Data Index: 2507467 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5608. Min Act: -0.1700
Data Index: 4077961 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5295. Min Act: -0.1700
Data Index: 7413555 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5138. Min Act: -0.1700
Data Index: 268584 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5138. Min Act: -0.1700
Data Index: 3300162 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5138. Min Act: -0.1700
Data Index: 8491351 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5138. Min Act: -0.1700
Data Index: 6907162 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5138. Min Act: -0.1700
Data Index: 3952157 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4982. Min Act: -0.1700
Data Index: 6332021 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4982. Min Act: -0.1700
Data Index: 4750387 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.5138. Min Act: -0.1700
Data Index: 7039336 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4669. Min Act: -0.1700
Data Index: 2511939 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4825. Min Act: -0.1700
Data Index: 1472036 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4669. Min Act: -0.1700
Data Index: 6955772 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4825. Min Act: -0.1700
Data Index: 3819997 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4825. Min Act: -0.1700
Data Index: 3350251 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4669. Min Act: -0.1700
Data Index: 2762276 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4825. Min Act: -0.1700
Data Index: 4313833 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5765. Min Range: -3.5765
Max Act: 3.4512. Min Act: -0.1700
Data Index: 6978109 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19