Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4165 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.4157. Min Act: -0.1700
Data Index: 6139031 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.3532. Min Act: -0.1700
Data Index: 7023820 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.3220. Min Act: -0.1700
Data Index: 6647938 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.2907. Min Act: -0.1700
Data Index: 7103670 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.3220. Min Act: -0.1700
Data Index: 985001 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.2907. Min Act: -0.1700
Data Index: 8500109 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.2595. Min Act: -0.1700
Data Index: 2832107 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.2282. Min Act: -0.1700
Data Index: 1307675 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.2282. Min Act: -0.1700
Data Index: 6942809 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.2282. Min Act: -0.1700
Data Index: 2857927 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1970. Min Act: -0.1700
Data Index: 8287017 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1970. Min Act: -0.1700
Data Index: 4032742 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1970. Min Act: -0.1700
Data Index: 8696315 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1970. Min Act: -0.1700
Data Index: 5295275 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1970. Min Act: -0.1700
Data Index: 2343119 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1657. Min Act: -0.1700
Data Index: 82213 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1657. Min Act: -0.1700
Data Index: 7562387 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1657. Min Act: -0.1700
Data Index: 7254007 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1657. Min Act: -0.1700
Data Index: 6781605 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4157. Min Range: -6.4157
Max Act: 6.1345. Min Act: -0.1700
Data Index: 1940990 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19