Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4428 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.4386. Min Act: -0.1700
Data Index: 2579529 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.3761. Min Act: -0.1700
Data Index: 1306857 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.3449. Min Act: -0.1700
Data Index: 5626485 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.3136. Min Act: -0.1700
Data Index: 4325141 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.3136. Min Act: -0.1700
Data Index: 5746303 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.2511. Min Act: -0.1700
Data Index: 4938346 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.2199. Min Act: -0.1700
Data Index: 4847995 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.2511. Min Act: -0.1700
Data Index: 5692967 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.2199. Min Act: -0.1699
Data Index: 3931769 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.1261. Min Act: -0.1700
Data Index: 2886532 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.1261. Min Act: -0.1700
Data Index: 2943318 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0636. Min Act: -0.1700
Data Index: 5075735 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0636. Min Act: -0.1700
Data Index: 1469636 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0636. Min Act: -0.1700
Data Index: 8611403 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0636. Min Act: -0.1700
Data Index: 4115720 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0324. Min Act: -0.1700
Data Index: 1553965 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0324. Min Act: -0.1700
Data Index: 8332049 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0324. Min Act: -0.1700
Data Index: 1808760 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0324. Min Act: -0.1700
Data Index: 6410209 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4386. Min Range: -5.4386
Max Act: 5.0011. Min Act: -0.1700
Data Index: 3205103 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19