Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0570. Min Range: -3.0570
Max Act: 3.0570. Min Act: -0.1700
Data Index: 6168581 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0570. Min Range: -3.0570
Max Act: 3.0096. Min Act: -0.1700
Data Index: 4726345 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9938. Min Act: -0.1700
Data Index: 8498437 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9938. Min Act: -0.1700
Data Index: 3952187 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9938. Min Act: -0.1700
Data Index: 2820734 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9938. Min Act: -0.1700
Data Index: 3460901 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9938. Min Act: -0.1700
Data Index: 4936068 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9938. Min Act: -0.1700
Data Index: 8434554 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9780. Min Act: -0.1700
Data Index: 8020075 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9780. Min Act: -0.1700
Data Index: 3452981 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9780. Min Act: -0.1700
Data Index: 7346308 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9780. Min Act: -0.1700
Data Index: 1521703 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9622. Min Act: -0.1700
Data Index: 4979141 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9622. Min Act: -0.1700
Data Index: 7796220 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9622. Min Act: -0.1700
Data Index: 7541651 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9622. Min Act: -0.1700
Data Index: 6800224 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9622. Min Act: -0.1700
Data Index: 3363141 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9622. Min Act: -0.1700
Data Index: 3014857 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9622. Min Act: -0.1700
Data Index: 835139 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0570. Min Range: -3.0570
Max Act: 2.9622. Min Act: -0.1700
Data Index: 3833177 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19