Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.5438. Min Act: -0.1700
Data Index: 3662537 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.5115. Min Act: -0.1700
Data Index: 7908380 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.5115. Min Act: -0.1700
Data Index: 4710676 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4466. Min Act: -0.1700
Data Index: 5034953 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4466. Min Act: -0.1700
Data Index: 5558964 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4791. Min Act: -0.1700
Data Index: 3971829 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4303. Min Act: -0.1700
Data Index: 4668493 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4303. Min Act: -0.1700
Data Index: 883935 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4466. Min Act: -0.1700
Data Index: 2456011 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4303. Min Act: -0.1700
Data Index: 2802089 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4140. Min Act: -0.1700
Data Index: 2364670 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4140. Min Act: -0.1700
Data Index: 1719234 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4140. Min Act: -0.1700
Data Index: 6716146 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4140. Min Act: -0.1700
Data Index: 8663597 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4303. Min Act: -0.1700
Data Index: 8491485 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.4140. Min Act: -0.1700
Data Index: 8422540 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.3977. Min Act: -0.1700
Data Index: 3651022 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.3814. Min Act: -0.1700
Data Index: 3871283 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.3814. Min Act: -0.1700
Data Index: 6708712 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5438. Min Range: -2.5438
Max Act: 2.3814. Min Act: -0.1700
Data Index: 6597432 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19