Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.7312. Min Act: -0.1700
Data Index: 2830028 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.6062. Min Act: -0.1700
Data Index: 7467838 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.6062. Min Act: -0.1700
Data Index: 6638732 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.5437. Min Act: -0.1700
Data Index: 5179900 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.5124. Min Act: -0.1700
Data Index: 4584690 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.5124. Min Act: -0.1700
Data Index: 2175621 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4499. Min Act: -0.1700
Data Index: 2506399 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4812. Min Act: -0.1700
Data Index: 3519826 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4499. Min Act: -0.1700
Data Index: 6657671 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4499. Min Act: -0.1700
Data Index: 2594868 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4499. Min Act: -0.1700
Data Index: 2615782 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4499. Min Act: -0.1700
Data Index: 2511430 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4499. Min Act: -0.1700
Data Index: 7259087 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3874. Min Act: -0.1700
Data Index: 1630664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4187. Min Act: -0.1700
Data Index: 984758 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3874. Min Act: -0.1700
Data Index: 8177676 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3874. Min Act: -0.1700
Data Index: 4194510 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3874. Min Act: -0.1700
Data Index: 8120206 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3561. Min Act: -0.1700
Data Index: 2691100 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3561. Min Act: -0.1700
Data Index: 1242965 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19