Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.5848. Min Act: -0.1700
Data Index: 2025347 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.4286. Min Act: -0.1700
Data Index: 7843630 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.3661. Min Act: -0.1700
Data Index: 6867821 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.3973. Min Act: -0.1700
Data Index: 4441981 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.3661. Min Act: -0.1700
Data Index: 5015987 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.3348. Min Act: -0.1700
Data Index: 8367526 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.3348. Min Act: -0.1700
Data Index: 3391184 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.3036. Min Act: -0.1700
Data Index: 6231428 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.3036. Min Act: -0.1689
Data Index: 2318198 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.3036. Min Act: -0.1700
Data Index: 1821831 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2723. Min Act: -0.1700
Data Index: 6654898 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2723. Min Act: -0.1700
Data Index: 3368811 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2411. Min Act: -0.1700
Data Index: 6232380 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2723. Min Act: -0.1700
Data Index: 5102541 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2411. Min Act: -0.1700
Data Index: 6752660 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2411. Min Act: -0.1700
Data Index: 5573877 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2723. Min Act: -0.1700
Data Index: 3523623 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2411. Min Act: -0.1700
Data Index: 2770279 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2411. Min Act: -0.1700
Data Index: 8051271 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5848. Min Range: -6.5848
Max Act: 6.2098. Min Act: -0.1700
Data Index: 668389 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19