Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.6032. Min Act: -0.1700
Data Index: 7050147 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.4782. Min Act: -0.1700
Data Index: 1364587 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.4782. Min Act: -0.1700
Data Index: 8105594 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.4782. Min Act: -0.1700
Data Index: 187934 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.4157. Min Act: -0.1700
Data Index: 4051582 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.3532. Min Act: -0.1700
Data Index: 4534043 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.2907. Min Act: -0.1700
Data Index: 3447404 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.2907. Min Act: -0.1700
Data Index: 7803066 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.2282. Min Act: -0.1700
Data Index: 8286419 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.1657. Min Act: -0.1700
Data Index: 3678020 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.2282. Min Act: -0.1700
Data Index: 868712 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.1657. Min Act: -0.1700
Data Index: 6758633 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.1657. Min Act: -0.1700
Data Index: 5048656 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.1657. Min Act: -0.1700
Data Index: 3969457 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.1657. Min Act: -0.1700
Data Index: 4006371 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.1032. Min Act: -0.1700
Data Index: 3739257 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.1032. Min Act: -0.1700
Data Index: 5464910 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.0407. Min Act: -0.1700
Data Index: 2205077 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6032. Min Range: -8.6032
Max Act: 8.0407. Min Act: -0.1700
Data Index: 353540 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6032. Min Range: -8.6032
Max Act: 7.9782. Min Act: -0.1700
Data Index: 5284637 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19