Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.9315. Min Act: -0.1700
Data Index: 5682652 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.7752. Min Act: -0.1700
Data Index: 2679842 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.7752. Min Act: -0.1700
Data Index: 8330014 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.7440. Min Act: -0.1700
Data Index: 4435045 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.7127. Min Act: -0.1700
Data Index: 8307661 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.7127. Min Act: -0.1700
Data Index: 2944819 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.6815. Min Act: -0.1700
Data Index: 3057240 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.7127. Min Act: -0.1700
Data Index: 3032841 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.6502. Min Act: -0.1700
Data Index: 1388413 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5877. Min Act: -0.1700
Data Index: 2492541 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5877. Min Act: -0.1700
Data Index: 6666653 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5877. Min Act: -0.1700
Data Index: 2246454 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5877. Min Act: -0.1700
Data Index: 8754244 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5877. Min Act: -0.1700
Data Index: 4655515 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5565. Min Act: -0.1700
Data Index: 5157534 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5565. Min Act: -0.1700
Data Index: 5374262 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5252. Min Act: -0.1700
Data Index: 3503588 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5252. Min Act: -0.1700
Data Index: 6028668 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.5252. Min Act: -0.1700
Data Index: 2300977 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9315. Min Range: -6.9315
Max Act: 6.4940. Min Act: -0.1700
Data Index: 5015229 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19