Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2043 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.7416. Min Act: -0.1700
Data Index: 7683200 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.6479. Min Act: -0.1700
Data Index: 649001 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.6166. Min Act: -0.1700
Data Index: 7971069 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.5854. Min Act: -0.1700
Data Index: 4628613 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.5541. Min Act: -0.1700
Data Index: 4145791 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.5541. Min Act: -0.1700
Data Index: 516287 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.4916. Min Act: -0.1700
Data Index: 4772219 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.4604. Min Act: -0.1700
Data Index: 8140302 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.4291. Min Act: -0.1700
Data Index: 6028641 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.4291. Min Act: -0.1700
Data Index: 2281035 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.4291. Min Act: -0.1700
Data Index: 257070 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.3979. Min Act: -0.1700
Data Index: 6081427 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.3979. Min Act: -0.1700
Data Index: 8077557 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.4291. Min Act: -0.1700
Data Index: 261353 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.3666. Min Act: -0.1700
Data Index: 417347 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.3666. Min Act: -0.1700
Data Index: 1414248 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.3666. Min Act: -0.1700
Data Index: 7383922 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.3666. Min Act: -0.1700
Data Index: 1460050 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.3666. Min Act: -0.1700
Data Index: 3591454 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7416. Min Range: -5.7416
Max Act: 5.3979. Min Act: -0.1700
Data Index: 1571050 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19