Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 101 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.6503. Min Act: -0.1700
Data Index: 1434061 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.6190. Min Act: -0.1700
Data Index: 1326466 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.5094. Min Act: -0.1700
Data Index: 5185288 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.4938. Min Act: -0.1700
Data Index: 3510309 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.4624. Min Act: -0.1700
Data Index: 555242 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.4624. Min Act: -0.1700
Data Index: 1073662 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.4468. Min Act: -0.1700
Data Index: 2198954 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.4311. Min Act: -0.1700
Data Index: 6780325 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.4154. Min Act: -0.1700
Data Index: 2471225 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.4154. Min Act: -0.1700
Data Index: 5401579 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3997. Min Act: -0.1700
Data Index: 8088452 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3997. Min Act: -0.1700
Data Index: 2409654 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3841. Min Act: -0.1700
Data Index: 1645461 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3684. Min Act: -0.1700
Data Index: 3485902 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3997. Min Act: -0.1700
Data Index: 1063623 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3684. Min Act: -0.1700
Data Index: 1114963 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3684. Min Act: -0.1700
Data Index: 4363582 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3527. Min Act: -0.1700
Data Index: 910819 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3527. Min Act: -0.1700
Data Index: 3788171 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6503. Min Range: -3.6503
Max Act: 3.3370. Min Act: -0.1700
Data Index: 5006292 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19