Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4760 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0436. Min Range: -5.0436
Max Act: 5.0436. Min Act: -0.1700
Data Index: 8142157 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9498. Min Act: -0.1700
Data Index: 7885755 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9498. Min Act: -0.1700
Data Index: 1743195 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.9186. Min Act: -0.1700
Data Index: 8123376 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8873. Min Act: -0.1700
Data Index: 7777324 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8873. Min Act: -0.1700
Data Index: 1819233 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8873. Min Act: -0.1700
Data Index: 8142158 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8561. Min Act: -0.1700
Data Index: 2706687 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8561. Min Act: -0.1700
Data Index: 8123371 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8248. Min Act: -0.1700
Data Index: 1190955 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7936. Min Act: -0.1700
Data Index: 3168795 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.8248. Min Act: -0.1700
Data Index: 5033800 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7936. Min Act: -0.1700
Data Index: 1092198 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7623. Min Act: -0.1700
Data Index: 3550984 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7623. Min Act: -0.1700
Data Index: 6810463 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7623. Min Act: -0.1700
Data Index: 3639627 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7623. Min Act: -0.1700
Data Index: 7217286 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7311. Min Act: -0.1700
Data Index: 332207 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7311. Min Act: -0.1700
Data Index: 7055927 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0436. Min Range: -5.0436
Max Act: 4.7311. Min Act: -0.1700
Data Index: 1721567 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19