Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.7350. Min Act: -0.1700
Data Index: 4474169 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.6725. Min Act: -0.1700
Data Index: 5793635 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.5162. Min Act: -0.1700
Data Index: 4474181 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.4225. Min Act: -0.1700
Data Index: 8518057 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.4225. Min Act: -0.1700
Data Index: 4474180 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.3912. Min Act: -0.1700
Data Index: 3435364 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.3912. Min Act: -0.1700
Data Index: 8791285 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.3287. Min Act: -0.1700
Data Index: 8682693 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2975. Min Act: -0.1700
Data Index: 3294883 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2662. Min Act: -0.1700
Data Index: 1687937 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2662. Min Act: -0.1700
Data Index: 931100 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2662. Min Act: -0.1700
Data Index: 7141269 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2662. Min Act: -0.1700
Data Index: 7075309 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2350. Min Act: -0.1700
Data Index: 8026673 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2350. Min Act: -0.1700
Data Index: 1485635 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2037. Min Act: -0.1700
Data Index: 4276192 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2037. Min Act: -0.1700
Data Index: 8791286 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2037. Min Act: -0.1700
Data Index: 137646 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2037. Min Act: -0.1700
Data Index: 1851973 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7350. Min Range: -6.7350
Max Act: 6.2350. Min Act: -0.1700
Data Index: 2087470 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19