Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.5498. Min Act: -0.1700
Data Index: 2794683 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.4873. Min Act: -0.1700
Data Index: 7477729 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.4560. Min Act: -0.1700
Data Index: 8004507 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.4248. Min Act: -0.1700
Data Index: 8454464 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.4248. Min Act: -0.1700
Data Index: 8016881 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.3310. Min Act: -0.1700
Data Index: 3248648 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.3935. Min Act: -0.1700
Data Index: 261278 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.3623. Min Act: -0.1700
Data Index: 1194089 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.3310. Min Act: -0.1700
Data Index: 3028757 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2998. Min Act: -0.1700
Data Index: 218190 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.3310. Min Act: -0.1700
Data Index: 1776795 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.3310. Min Act: -0.1700
Data Index: 5520141 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2998. Min Act: -0.1700
Data Index: 510009 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2998. Min Act: -0.1700
Data Index: 1521634 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2685. Min Act: -0.1700
Data Index: 5003577 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2373. Min Act: -0.1700
Data Index: 5970675 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2685. Min Act: -0.1700
Data Index: 6925133 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2998. Min Act: -0.1700
Data Index: 7359698 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2685. Min Act: -0.1700
Data Index: 4591031 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5498. Min Range: -5.5498
Max Act: 5.2373. Min Act: -0.1700
Data Index: 3619802 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19