Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5386 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.3983. Min Act: -0.1700
Data Index: 3641360 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.3358. Min Act: -0.1700
Data Index: 4547460 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.3358. Min Act: -0.1700
Data Index: 1117001 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.2108. Min Act: -0.1700
Data Index: 6598455 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.0858. Min Act: -0.1700
Data Index: 2159289 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.0858. Min Act: -0.1700
Data Index: 2639857 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.0858. Min Act: -0.1700
Data Index: 8344341 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.0858. Min Act: -0.1700
Data Index: 400856 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.0858. Min Act: -0.1700
Data Index: 2320802 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.0233. Min Act: -0.1700
Data Index: 7282260 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3983. Min Range: -8.3983
Max Act: 8.0233. Min Act: -0.1700
Data Index: 7719774 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.9608. Min Act: -0.1700
Data Index: 1369301 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.9608. Min Act: -0.1700
Data Index: 2591010 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.9608. Min Act: -0.1700
Data Index: 3381690 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.8983. Min Act: -0.1700
Data Index: 335247 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.8983. Min Act: -0.1700
Data Index: 4756674 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.8358. Min Act: -0.1700
Data Index: 3774716 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.7733. Min Act: -0.1700
Data Index: 6978635 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.7733. Min Act: -0.1700
Data Index: 1323468 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3983. Min Range: -8.3983
Max Act: 7.7733. Min Act: -0.1700
Data Index: 7915146 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19