Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1611 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.8452. Min Act: -0.1700
Data Index: 6215940 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.7513. Min Act: -0.1700
Data Index: 5809098 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.7201. Min Act: -0.1700
Data Index: 7623920 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.7201. Min Act: -0.1700
Data Index: 7213095 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.6731. Min Act: -0.1700
Data Index: 666189 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.6731. Min Act: -0.1700
Data Index: 4939962 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.6262. Min Act: -0.1700
Data Index: 4935258 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.6418. Min Act: -0.1700
Data Index: 3503512 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.6262. Min Act: -0.1700
Data Index: 7892916 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.6262. Min Act: -0.1700
Data Index: 8339001 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.6105. Min Act: -0.1700
Data Index: 7031473 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5792. Min Act: -0.1700
Data Index: 3147143 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5792. Min Act: -0.1700
Data Index: 6128720 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5636. Min Act: -0.1700
Data Index: 7936026 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5636. Min Act: -0.1700
Data Index: 6739981 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5479. Min Act: -0.1700
Data Index: 6093917 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5479. Min Act: -0.1700
Data Index: 4866946 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5479. Min Act: -0.1700
Data Index: 324090 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5479. Min Act: -0.1700
Data Index: 3378150 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8452. Min Range: -3.8452
Max Act: 3.5323. Min Act: -0.1700
Data Index: 6173677 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19