Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2360 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0067. Min Range: -5.0067
Max Act: 5.0067. Min Act: -0.1700
Data Index: 6677613 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.9129. Min Act: -0.1700
Data Index: 297660 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.8504. Min Act: -0.1700
Data Index: 2723456 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.8192. Min Act: -0.1700
Data Index: 7067196 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.8192. Min Act: -0.1700
Data Index: 979461 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7879. Min Act: -0.1700
Data Index: 6977329 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7879. Min Act: -0.1700
Data Index: 4000908 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7879. Min Act: -0.1700
Data Index: 164757 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7879. Min Act: -0.1700
Data Index: 875659 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7879. Min Act: -0.1700
Data Index: 8086652 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7567. Min Act: -0.1700
Data Index: 3832940 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7254. Min Act: -0.1700
Data Index: 4069861 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7254. Min Act: -0.1700
Data Index: 8047432 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7254. Min Act: -0.1700
Data Index: 3029811 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7567. Min Act: -0.1700
Data Index: 7919469 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.7254. Min Act: -0.1700
Data Index: 2478470 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.6942. Min Act: -0.1700
Data Index: 3169545 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.6942. Min Act: -0.1700
Data Index: 4951285 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.6942. Min Act: -0.1700
Data Index: 3571788 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0067. Min Range: -5.0067
Max Act: 4.6942. Min Act: -0.1700
Data Index: 1288988 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19