Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 336 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.6585. Min Act: -0.1700
Data Index: 4217278 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.4085. Min Act: -0.1700
Data Index: 313308 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.1897. Min Act: -0.1700
Data Index: 3236429 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.1897. Min Act: -0.1700
Data Index: 2383249 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.1585. Min Act: -0.1700
Data Index: 137304 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.1585. Min Act: -0.1700
Data Index: 2406931 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.1272. Min Act: -0.1700
Data Index: 329830 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.0960. Min Act: -0.1700
Data Index: 7660706 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.1272. Min Act: -0.1700
Data Index: 6955305 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.0647. Min Act: -0.1700
Data Index: 1196099 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.0335. Min Act: -0.1700
Data Index: 5661785 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.0335. Min Act: -0.1700
Data Index: 4044776 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6585. Min Range: -7.6585
Max Act: 7.0335. Min Act: -0.1700
Data Index: 5233182 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6585. Min Range: -7.6585
Max Act: 6.9710. Min Act: -0.1700
Data Index: 2221019 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6585. Min Range: -7.6585
Max Act: 6.9710. Min Act: -0.1700
Data Index: 5529362 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6585. Min Range: -7.6585
Max Act: 6.9710. Min Act: -0.1700
Data Index: 4638525 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6585. Min Range: -7.6585
Max Act: 6.9710. Min Act: -0.1700
Data Index: 7407202 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6585. Min Range: -7.6585
Max Act: 6.9710. Min Act: -0.1700
Data Index: 1018065 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6585. Min Range: -7.6585
Max Act: 6.9710. Min Act: -0.1700
Data Index: 6190551 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6585. Min Range: -7.6585
Max Act: 6.9397. Min Act: -0.1700
Data Index: 7081808 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19