Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2583. Min Range: -6.2583
Max Act: 6.2583. Min Act: -0.1700
Data Index: 1576855 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.8520. Min Act: -0.1699
Data Index: 916505 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.8208. Min Act: -0.1700
Data Index: 1439596 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.8833. Min Act: -0.1700
Data Index: 7286993 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.8208. Min Act: -0.1700
Data Index: 6848703 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.7583. Min Act: -0.1700
Data Index: 5307453 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.7895. Min Act: -0.1700
Data Index: 7772512 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.7583. Min Act: -0.1700
Data Index: 2759455 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.7583. Min Act: -0.1700
Data Index: 7554320 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.7270. Min Act: -0.1700
Data Index: 6069436 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6958. Min Act: -0.1700
Data Index: 4383826 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.7270. Min Act: -0.1700
Data Index: 7554319 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6958. Min Act: -0.1700
Data Index: 134512 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6958. Min Act: -0.1700
Data Index: 6976788 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6958. Min Act: -0.1700
Data Index: 4498384 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6958. Min Act: -0.1700
Data Index: 7865415 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6958. Min Act: -0.1700
Data Index: 2363380 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6645. Min Act: -0.1700
Data Index: 4724245 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6645. Min Act: -0.1700
Data Index: 7031750 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2583. Min Range: -6.2583
Max Act: 5.6645. Min Act: -0.1700
Data Index: 2789574 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19