Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2092. Min Range: -6.2092
Max Act: 6.2092. Min Act: -0.1700
Data Index: 6333500 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2092. Min Range: -6.2092
Max Act: 6.1155. Min Act: -0.1700
Data Index: 5181314 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2092. Min Range: -6.2092
Max Act: 6.0530. Min Act: -0.1700
Data Index: 3715102 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.9905. Min Act: -0.1700
Data Index: 4839339 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.9905. Min Act: -0.1700
Data Index: 2054268 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.9280. Min Act: -0.1700
Data Index: 6705710 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.8967. Min Act: -0.1700
Data Index: 2068056 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.8342. Min Act: -0.1700
Data Index: 1531096 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.7092. Min Act: -0.1700
Data Index: 6478018 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.7717. Min Act: -0.1700
Data Index: 6452579 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.7405. Min Act: -0.1700
Data Index: 1272068 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.7092. Min Act: -0.1700
Data Index: 1668026 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.6780. Min Act: -0.1700
Data Index: 8811613 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.6780. Min Act: -0.1700
Data Index: 2741507 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.6780. Min Act: -0.1700
Data Index: 439382 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.6467. Min Act: -0.1700
Data Index: 4729788 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.6467. Min Act: -0.1700
Data Index: 8004983 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.6155. Min Act: -0.1700
Data Index: 1030698 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.5842. Min Act: -0.1700
Data Index: 4966256 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2092. Min Range: -6.2092
Max Act: 5.5842. Min Act: -0.1700
Data Index: 7042862 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19