Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4060 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1183. Min Range: -8.1183
Max Act: 8.1183. Min Act: -0.1700
Data Index: 810463 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7433. Min Act: -0.1700
Data Index: 8093116 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7433. Min Act: -0.1700
Data Index: 4005614 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7433. Min Act: -0.1700
Data Index: 4372382 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.6808. Min Act: -0.1700
Data Index: 7581038 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.6808. Min Act: -0.1700
Data Index: 6074789 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7433. Min Act: -0.1700
Data Index: 5361383 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.6808. Min Act: -0.1700
Data Index: 4638370 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.6496. Min Act: -0.1700
Data Index: 4173319 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.6808. Min Act: -0.1700
Data Index: 7500304 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7121. Min Act: -0.1700
Data Index: 6297730 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7433. Min Act: -0.1700
Data Index: 3292164 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7433. Min Act: -0.1700
Data Index: 3126688 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7121. Min Act: -0.1700
Data Index: 2088170 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7121. Min Act: -0.1700
Data Index: 8595329 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.6808. Min Act: -0.1700
Data Index: 3357074 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.6183. Min Act: -0.1700
Data Index: 4237225 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7121. Min Act: -0.1700
Data Index: 375105 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.7121. Min Act: -0.1700
Data Index: 8416938 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1183. Min Range: -8.1183
Max Act: 7.6808. Min Act: -0.1700
Data Index: 5527516 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19