Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3973 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0956. Min Range: -4.0956
Max Act: 4.0956. Min Act: -0.1700
Data Index: 5135858 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.8455. Min Act: -0.1700
Data Index: 7869214 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.8455. Min Act: -0.1700
Data Index: 6655769 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.8455. Min Act: -0.1700
Data Index: 3953303 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.8455. Min Act: -0.1700
Data Index: 1349014 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.8142. Min Act: -0.1700
Data Index: 5439851 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.8142. Min Act: -0.1700
Data Index: 8732305 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.8142. Min Act: -0.1700
Data Index: 8303304 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.8142. Min Act: -0.1700
Data Index: 4798510 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7830. Min Act: -0.1700
Data Index: 4456345 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7830. Min Act: -0.1700
Data Index: 4704684 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7830. Min Act: -0.1700
Data Index: 8603622 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7830. Min Act: -0.1700
Data Index: 2570033 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7204. Min Act: -0.1700
Data Index: 5126563 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7830. Min Act: -0.1700
Data Index: 4824037 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7517. Min Act: -0.1700
Data Index: 6267115 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7204. Min Act: -0.1700
Data Index: 329005 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7204. Min Act: -0.1700
Data Index: 2423903 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7204. Min Act: -0.1700
Data Index: 7006309 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0956. Min Range: -4.0956
Max Act: 3.7204. Min Act: -0.1700
Data Index: 1806638 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19