Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0873. Min Range: -7.0873
Max Act: 7.0873. Min Act: -0.1700
Data Index: 3295620 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.9310. Min Act: -0.1700
Data Index: 5688015 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.8685. Min Act: -0.1700
Data Index: 5125537 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.8373. Min Act: -0.1700
Data Index: 281152 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.8373. Min Act: -0.1700
Data Index: 2389034 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.7435. Min Act: -0.1700
Data Index: 486490 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.7435. Min Act: -0.1700
Data Index: 7595699 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.7123. Min Act: -0.1700
Data Index: 7409340 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.7123. Min Act: -0.1700
Data Index: 3734574 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.7123. Min Act: -0.1700
Data Index: 1660079 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.6810. Min Act: -0.1700
Data Index: 2519233 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.6810. Min Act: -0.1700
Data Index: 2940254 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.6498. Min Act: -0.1700
Data Index: 663659 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.6185. Min Act: -0.1700
Data Index: 2281948 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.6185. Min Act: -0.1700
Data Index: 449181 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.6185. Min Act: -0.1700
Data Index: 6081057 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.5873. Min Act: -0.1700
Data Index: 292586 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.6185. Min Act: -0.1700
Data Index: 2382109 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.5873. Min Act: -0.1700
Data Index: 3876054 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0873. Min Range: -7.0873
Max Act: 6.5873. Min Act: -0.1700
Data Index: 7046284 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19