Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4540 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.8966. Min Act: -0.1700
Data Index: 3005735 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.8341. Min Act: -0.1700
Data Index: 4042781 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.8029. Min Act: -0.1700
Data Index: 4954248 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.6466. Min Act: -0.1700
Data Index: 4035574 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.6154. Min Act: -0.1700
Data Index: 4689766 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.5841. Min Act: -0.1700
Data Index: 8313287 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.5529. Min Act: -0.1700
Data Index: 7555634 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.5529. Min Act: -0.1700
Data Index: 2339344 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.5216. Min Act: -0.1700
Data Index: 1615692 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.4591. Min Act: -0.1700
Data Index: 8597628 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.4904. Min Act: -0.1700
Data Index: 5967087 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.4904. Min Act: -0.1700
Data Index: 1985296 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.4904. Min Act: -0.1700
Data Index: 6839157 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.4591. Min Act: -0.1700
Data Index: 25571 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.4591. Min Act: -0.1700
Data Index: 3869437 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.3966. Min Act: -0.1700
Data Index: 4604425 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.3966. Min Act: -0.1700
Data Index: 7821608 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.3654. Min Act: -0.1700
Data Index: 4768117 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.3341. Min Act: -0.1700
Data Index: 6754211 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8966. Min Range: -6.8966
Max Act: 6.3341. Min Act: -0.1700
Data Index: 5521339 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19