Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.5231. Min Act: -0.1700
Data Index: 5166644 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.3981. Min Act: -0.1700
Data Index: 5571911 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.3668. Min Act: -0.1700
Data Index: 2366933 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.3356. Min Act: -0.1700
Data Index: 549885 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.2106. Min Act: -0.1700
Data Index: 6912810 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.1793. Min Act: -0.1700
Data Index: 4094894 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.1793. Min Act: -0.1700
Data Index: 7694552 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.1168. Min Act: -0.1700
Data Index: 3905122 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.1168. Min Act: -0.1700
Data Index: 7281765 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.1168. Min Act: -0.1700
Data Index: 6862433 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.0856. Min Act: -0.1700
Data Index: 5035183 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.0543. Min Act: -0.1700
Data Index: 1602852 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.0543. Min Act: -0.1700
Data Index: 3142406 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.0543. Min Act: -0.1700
Data Index: 3584494 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.0543. Min Act: -0.1700
Data Index: 4244148 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5231. Min Range: -6.5231
Max Act: 5.9918. Min Act: -0.1700
Data Index: 2677040 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.0231. Min Act: -0.1700
Data Index: 3501927 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5231. Min Range: -6.5231
Max Act: 6.0231. Min Act: -0.1700
Data Index: 7325620 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5231. Min Range: -6.5231
Max Act: 5.9918. Min Act: -0.1700
Data Index: 6689554 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5231. Min Range: -6.5231
Max Act: 5.9918. Min Act: -0.1700
Data Index: 5004136 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19