Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.3046. Min Act: -0.1700
Data Index: 5465816 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.2108. Min Act: -0.1700
Data Index: 4517979 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1796. Min Act: -0.1700
Data Index: 6260139 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1796. Min Act: -0.1700
Data Index: 5162592 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1483. Min Act: -0.1700
Data Index: 707012 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1483. Min Act: -0.1700
Data Index: 8344490 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.1171. Min Act: -0.1700
Data Index: 121532 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0858. Min Act: -0.1700
Data Index: 7570509 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0546. Min Act: -0.1700
Data Index: 4162757 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0233. Min Act: -0.1700
Data Index: 4778464 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3046. Min Range: -5.3046
Max Act: 5.0546. Min Act: -0.1700
Data Index: 813367 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9921. Min Act: -0.1700
Data Index: 7771296 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9921. Min Act: -0.1700
Data Index: 6883709 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9921. Min Act: -0.1700
Data Index: 1975649 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9921. Min Act: -0.1700
Data Index: 8538680 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9921. Min Act: -0.1700
Data Index: 8067390 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9608. Min Act: -0.1700
Data Index: 1435163 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9608. Min Act: -0.1700
Data Index: 3604615 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9296. Min Act: -0.1700
Data Index: 5487301 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3046. Min Range: -5.3046
Max Act: 4.9296. Min Act: -0.1700
Data Index: 2009466 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19