Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0067. Min Range: -9.0067
Max Act: 9.0067. Min Act: -0.1700
Data Index: 3244470 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.8817. Min Act: -0.1700
Data Index: 7306967 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.8192. Min Act: -0.1700
Data Index: 4855623 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.7567. Min Act: -0.1700
Data Index: 2224473 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.8192. Min Act: -0.1700
Data Index: 1294284 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.7567. Min Act: -0.1700
Data Index: 3102938 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.8817. Min Act: -0.1700
Data Index: 8480332 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.7567. Min Act: -0.1700
Data Index: 4127773 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.7567. Min Act: -0.1700
Data Index: 7077570 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.7567. Min Act: -0.1700
Data Index: 4523638 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.7567. Min Act: -0.1700
Data Index: 1922587 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.6942. Min Act: -0.1700
Data Index: 2796949 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.6942. Min Act: -0.1700
Data Index: 2598437 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.6942. Min Act: -0.1700
Data Index: 91918 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.6317. Min Act: -0.1700
Data Index: 2272436 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.6317. Min Act: -0.1700
Data Index: 6390287 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.5692. Min Act: -0.1700
Data Index: 6450652 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.6317. Min Act: -0.1700
Data Index: 6018808 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.6317. Min Act: -0.1700
Data Index: 3976142 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0067. Min Range: -9.0067
Max Act: 8.6942. Min Act: -0.1700
Data Index: 2595863 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19