Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.9013. Min Act: -0.1700
Data Index: 5489454 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.8700. Min Act: -0.1700
Data Index: 8409941 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.7450. Min Act: -0.1700
Data Index: 6357646 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.6513. Min Act: -0.1700
Data Index: 1786093 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.5888. Min Act: -0.1700
Data Index: 7578445 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.5575. Min Act: -0.1700
Data Index: 2834417 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.5263. Min Act: -0.1700
Data Index: 2293184 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.4013. Min Act: -0.1700
Data Index: 3668443 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.3700. Min Act: -0.1700
Data Index: 5620928 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.3700. Min Act: -0.1700
Data Index: 8726322 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.3388. Min Act: -0.1700
Data Index: 8092841 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.3388. Min Act: -0.1700
Data Index: 3496398 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.3700. Min Act: -0.1700
Data Index: 6476235 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.2763. Min Act: -0.1700
Data Index: 4789602 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.2763. Min Act: -0.1700
Data Index: 2319630 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.2450. Min Act: -0.1700
Data Index: 4388866 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.2450. Min Act: -0.1700
Data Index: 7578442 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.2763. Min Act: -0.1700
Data Index: 7377489 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.2138. Min Act: -0.1700
Data Index: 6027204 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9013. Min Range: -6.9013
Max Act: 6.2138. Min Act: -0.1700
Data Index: 8192351 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19