Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0175. Min Range: -3.0175
Max Act: 3.0175. Min Act: -0.1700
Data Index: 1853578 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.9226. Min Act: -0.1700
Data Index: 8728178 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.8432. Min Act: -0.1700
Data Index: 7907499 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7796. Min Act: -0.1700
Data Index: 2039515 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7796. Min Act: -0.1700
Data Index: 893540 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7796. Min Act: -0.1700
Data Index: 5032717 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7796. Min Act: -0.1700
Data Index: 6169339 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7477. Min Act: -0.1700
Data Index: 1776556 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7636. Min Act: -0.1700
Data Index: 7115093 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7477. Min Act: -0.1700
Data Index: 3455980 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7477. Min Act: -0.1700
Data Index: 5480499 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7157. Min Act: -0.1700
Data Index: 6171858 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7157. Min Act: -0.1700
Data Index: 2110106 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7157. Min Act: -0.1700
Data Index: 1547670 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7157. Min Act: -0.1700
Data Index: 4142801 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.6997. Min Act: -0.1700
Data Index: 2955546 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.7157. Min Act: -0.1700
Data Index: 3310294 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.6837. Min Act: -0.1700
Data Index: 7751001 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.6997. Min Act: -0.1700
Data Index: 7564786 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0175. Min Range: -3.0175
Max Act: 2.6837. Min Act: -0.1700
Data Index: 4080167 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19