Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1523. Min Range: -6.1523
Max Act: 6.1523. Min Act: -0.1700
Data Index: 8593478 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.9648. Min Act: -0.1700
Data Index: 8315221 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.7773. Min Act: -0.1700
Data Index: 1605400 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.7148. Min Act: -0.1700
Data Index: 7875428 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.5898. Min Act: -0.1700
Data Index: 3286223 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.5585. Min Act: -0.1700
Data Index: 4811050 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.4960. Min Act: -0.1700
Data Index: 2083158 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.4648. Min Act: -0.1700
Data Index: 4027938 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.4648. Min Act: -0.1700
Data Index: 7275556 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.4335. Min Act: -0.1700
Data Index: 100867 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.4335. Min Act: -0.1700
Data Index: 1135087 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.4335. Min Act: -0.1700
Data Index: 6069828 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.4023. Min Act: -0.1700
Data Index: 3772832 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.3710. Min Act: -0.1700
Data Index: 408320 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.4023. Min Act: -0.1700
Data Index: 7887374 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.3085. Min Act: -0.1700
Data Index: 5368774 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.3398. Min Act: -0.1700
Data Index: 647440 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.3085. Min Act: -0.1700
Data Index: 1254699 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.3085. Min Act: -0.1700
Data Index: 1301749 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1523. Min Range: -6.1523
Max Act: 5.3085. Min Act: -0.1700
Data Index: 3664888 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19