Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4563 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.1648. Min Act: -0.1700
Data Index: 4659470 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.1336. Min Act: -0.1700
Data Index: 113458 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 3029521 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 4350058 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 6202772 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.9773. Min Act: -0.1700
Data Index: 7823025 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.9461. Min Act: -0.1700
Data Index: 4330301 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.9461. Min Act: -0.1700
Data Index: 2185784 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.9773. Min Act: -0.1700
Data Index: 4391681 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.9148. Min Act: -0.1700
Data Index: 129130 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.8523. Min Act: -0.1700
Data Index: 3812057 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.8836. Min Act: -0.1700
Data Index: 262142 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.8523. Min Act: -0.1700
Data Index: 920015 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.8211. Min Act: -0.1700
Data Index: 2189677 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.8211. Min Act: -0.1700
Data Index: 5276075 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.8211. Min Act: -0.1700
Data Index: 707988 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.8211. Min Act: -0.1700
Data Index: 4834180 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.7586. Min Act: -0.1700
Data Index: 3168107 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.7273. Min Act: -0.1700
Data Index: 600957 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.7273. Min Act: -0.1700
Data Index: 7103591 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19