Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4816. Min Range: -7.4816
Max Act: 7.4816. Min Act: -0.1700
Data Index: 6314775 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4816. Min Range: -7.4816
Max Act: 7.1379. Min Act: -0.1700
Data Index: 6164744 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4816. Min Range: -7.4816
Max Act: 7.0441. Min Act: -0.1700
Data Index: 6876051 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.9816. Min Act: -0.1700
Data Index: 5498490 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.9191. Min Act: -0.1700
Data Index: 2366045 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.9191. Min Act: -0.1700
Data Index: 1887072 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.8566. Min Act: -0.1700
Data Index: 4602412 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.8254. Min Act: -0.1700
Data Index: 2332145 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.7941. Min Act: -0.1700
Data Index: 7261054 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.7629. Min Act: -0.1700
Data Index: 985289 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6691. Min Act: -0.1700
Data Index: 2013374 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6691. Min Act: -0.1700
Data Index: 3591952 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6691. Min Act: -0.1700
Data Index: 1084072 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6691. Min Act: -0.1700
Data Index: 3157148 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6691. Min Act: -0.1700
Data Index: 9260 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6379. Min Act: -0.1700
Data Index: 8163344 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6066. Min Act: -0.1700
Data Index: 1785807 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6379. Min Act: -0.1700
Data Index: 3404297 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6379. Min Act: -0.1700
Data Index: 4497066 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4816. Min Range: -7.4816
Max Act: 6.6066. Min Act: -0.1700
Data Index: 111191 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19