Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3801 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0916. Min Range: -5.0916
Max Act: 5.0916. Min Act: -0.1700
Data Index: 4453177 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0916. Min Range: -5.0916
Max Act: 5.0916. Min Act: -0.1700
Data Index: 2541621 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0916. Min Range: -5.0916
Max Act: 5.0291. Min Act: -0.1700
Data Index: 8575876 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0916. Min Range: -5.0916
Max Act: 5.0291. Min Act: -0.1700
Data Index: 5162662 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0916. Min Range: -5.0916
Max Act: 5.0291. Min Act: -0.1700
Data Index: 3266711 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9666. Min Act: -0.1700
Data Index: 5922966 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9666. Min Act: -0.1700
Data Index: 6054139 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9666. Min Act: -0.1700
Data Index: 8657925 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9354. Min Act: -0.1700
Data Index: 6349277 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9354. Min Act: -0.1700
Data Index: 8543588 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9354. Min Act: -0.1700
Data Index: 3817518 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9041. Min Act: -0.1700
Data Index: 7902106 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.8729. Min Act: -0.1700
Data Index: 3816872 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9354. Min Act: -0.1700
Data Index: 2477669 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.9041. Min Act: -0.1700
Data Index: 3556058 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.8729. Min Act: -0.1700
Data Index: 397888 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.8729. Min Act: -0.1700
Data Index: 4719541 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.8729. Min Act: -0.1700
Data Index: 8608762 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.8416. Min Act: -0.1700
Data Index: 7836522 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0916. Min Range: -5.0916
Max Act: 4.8416. Min Act: -0.1700
Data Index: 4038086 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19