Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2546 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.9276. Min Act: -0.1700
Data Index: 5434534 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.8494. Min Act: -0.1700
Data Index: 14719 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.6774. Min Act: -0.1700
Data Index: 1160256 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.7087. Min Act: -0.1700
Data Index: 7121002 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.5992. Min Act: -0.1700
Data Index: 4725342 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.6617. Min Act: -0.1700
Data Index: 6891125 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.5835. Min Act: -0.1700
Data Index: 7630485 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.5365. Min Act: -0.1700
Data Index: 7615004 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.5522. Min Act: -0.1700
Data Index: 1913899 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.5522. Min Act: -0.1700
Data Index: 5589702 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.5052. Min Act: -0.1700
Data Index: 1674485 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.5052. Min Act: -0.1700
Data Index: 779604 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.4896. Min Act: -0.1700
Data Index: 1429853 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.4739. Min Act: -0.1700
Data Index: 5716876 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.4739. Min Act: -0.1700
Data Index: 8755995 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.4739. Min Act: -0.1700
Data Index: 7936991 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.4582. Min Act: -0.1700
Data Index: 7485663 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.4112. Min Act: -0.1700
Data Index: 6529071 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.5052. Min Act: -0.1700
Data Index: 523503 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9276. Min Range: -3.9276
Max Act: 3.4269. Min Act: -0.1700
Data Index: 4468871 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19