Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.6367. Min Act: -0.1700
Data Index: 4815546 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.5117. Min Act: -0.1700
Data Index: 6815655 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.4492. Min Act: -0.1700
Data Index: 6260708 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.4492. Min Act: -0.1700
Data Index: 1422935 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.4180. Min Act: -0.1700
Data Index: 117796 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.3242. Min Act: -0.1700
Data Index: 7845582 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2617. Min Act: -0.1700
Data Index: 5993423 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2930. Min Act: -0.1700
Data Index: 6701857 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2305. Min Act: -0.1700
Data Index: 417271 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2305. Min Act: -0.1700
Data Index: 5590331 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.1992. Min Act: -0.1700
Data Index: 4022219 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2305. Min Act: -0.1700
Data Index: 3292606 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2305. Min Act: -0.1700
Data Index: 6002724 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2305. Min Act: -0.1700
Data Index: 3170104 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2305. Min Act: -0.1700
Data Index: 2002244 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.2305. Min Act: -0.1700
Data Index: 3733748 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.1992. Min Act: -0.1700
Data Index: 572195 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.1992. Min Act: -0.1700
Data Index: 4250314 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.1680. Min Act: -0.1700
Data Index: 4535597 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6367. Min Range: -5.6367
Max Act: 5.1680. Min Act: -0.1700
Data Index: 2906628 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19