Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4713. Min Range: -7.4713
Max Act: 7.4713. Min Act: -0.1700
Data Index: 6097930 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4713. Min Range: -7.4713
Max Act: 7.2213. Min Act: -0.1700
Data Index: 3541931 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4713. Min Range: -7.4713
Max Act: 7.2213. Min Act: -0.1700
Data Index: 5354158 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4713. Min Range: -7.4713
Max Act: 7.0338. Min Act: -0.1700
Data Index: 5042175 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.9401. Min Act: -0.1700
Data Index: 8001615 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.9088. Min Act: -0.1700
Data Index: 3552607 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.8776. Min Act: -0.1700
Data Index: 4733926 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.8463. Min Act: -0.1700
Data Index: 976561 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.8463. Min Act: -0.1700
Data Index: 5187096 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.8151. Min Act: -0.1700
Data Index: 5121642 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.7213. Min Act: -0.1700
Data Index: 6401193 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.7213. Min Act: -0.1700
Data Index: 2990880 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.6588. Min Act: -0.1700
Data Index: 3485462 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.6588. Min Act: -0.1700
Data Index: 6117718 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.6588. Min Act: -0.1700
Data Index: 149194 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.6276. Min Act: -0.1700
Data Index: 4967392 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.5963. Min Act: -0.1700
Data Index: 6284177 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.5963. Min Act: -0.1700
Data Index: 8796062 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.5963. Min Act: -0.1700
Data Index: 1125443 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4713. Min Range: -7.4713
Max Act: 6.5338. Min Act: -0.1700
Data Index: 1586550 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19