Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5769 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.3429. Min Act: -0.1700
Data Index: 4713961 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.3429. Min Act: -0.1700
Data Index: 3966224 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.3116. Min Act: -0.1700
Data Index: 8241602 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.3116. Min Act: -0.1700
Data Index: 8060263 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.2491. Min Act: -0.1700
Data Index: 7903756 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.2179. Min Act: -0.1700
Data Index: 5940881 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1866. Min Act: -0.1700
Data Index: 6675973 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1866. Min Act: -0.1700
Data Index: 8741979 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.2179. Min Act: -0.1700
Data Index: 7318547 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1866. Min Act: -0.1700
Data Index: 3131633 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1554. Min Act: -0.1700
Data Index: 115981 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1554. Min Act: -0.1700
Data Index: 2914664 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1241. Min Act: -0.1700
Data Index: 3018335 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1241. Min Act: -0.1700
Data Index: 7866651 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1554. Min Act: -0.1700
Data Index: 6280150 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1241. Min Act: -0.1700
Data Index: 8241598 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.0929. Min Act: -0.1700
Data Index: 5986781 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1241. Min Act: -0.1700
Data Index: 2914673 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.1241. Min Act: -0.1700
Data Index: 55684 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3429. Min Range: -5.3429
Max Act: 5.0929. Min Act: -0.1700
Data Index: 2576137 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19