Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2362. Min Range: -7.2362
Max Act: 7.2362. Min Act: -0.1700
Data Index: 5481010 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2362. Min Range: -7.2362
Max Act: 7.2050. Min Act: -0.1700
Data Index: 2943204 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2362. Min Range: -7.2362
Max Act: 7.1737. Min Act: -0.1700
Data Index: 7913561 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.9550. Min Act: -0.1700
Data Index: 6634033 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.9550. Min Act: -0.1700
Data Index: 2456513 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.8300. Min Act: -0.1700
Data Index: 5573173 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.7675. Min Act: -0.1700
Data Index: 7880718 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.7675. Min Act: -0.1700
Data Index: 1912130 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.7675. Min Act: -0.1700
Data Index: 7409773 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.7050. Min Act: -0.1700
Data Index: 4949345 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.7050. Min Act: -0.1700
Data Index: 7002067 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.7362. Min Act: -0.1700
Data Index: 6589919 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.7050. Min Act: -0.1700
Data Index: 2407216 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.6737. Min Act: -0.1700
Data Index: 835570 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.7050. Min Act: -0.1700
Data Index: 1790969 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.6737. Min Act: -0.1700
Data Index: 8482546 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.6737. Min Act: -0.1700
Data Index: 5319748 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.6737. Min Act: -0.1700
Data Index: 8809550 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.6737. Min Act: -0.1700
Data Index: 6971288 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2362. Min Range: -7.2362
Max Act: 6.6425. Min Act: -0.1700
Data Index: 2151777 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19