Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0546. Min Range: -5.0546
Max Act: 5.0233. Min Act: -0.1700
Data Index: 6574018 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0546. Min Range: -5.0546
Max Act: 5.0546. Min Act: -0.1700
Data Index: 3046588 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.9296. Min Act: -0.1700
Data Index: 2518848 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8983. Min Act: -0.1700
Data Index: 8060576 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8983. Min Act: -0.1700
Data Index: 8445855 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8671. Min Act: -0.1700
Data Index: 4098503 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8671. Min Act: -0.1700
Data Index: 2273261 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8671. Min Act: -0.1700
Data Index: 3170329 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 334157 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 330936 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 69039 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 7910212 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 4921308 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 7080125 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 7010718 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 5084948 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8358. Min Act: -0.1700
Data Index: 8781626 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8046. Min Act: -0.1700
Data Index: 6323100 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8046. Min Act: -0.1700
Data Index: 4355538 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0546. Min Range: -5.0546
Max Act: 4.8046. Min Act: -0.1700
Data Index: 1188490 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19