Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.7202. Min Act: -0.1700
Data Index: 7750729 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.5639. Min Act: -0.1700
Data Index: 6047695 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.5327. Min Act: -0.1700
Data Index: 8137092 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.5014. Min Act: -0.1700
Data Index: 3174114 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.4702. Min Act: -0.1700
Data Index: 5039512 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.4077. Min Act: -0.1700
Data Index: 3847004 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.3764. Min Act: -0.1700
Data Index: 2186063 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.3139. Min Act: -0.1700
Data Index: 7497040 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.3139. Min Act: -0.1700
Data Index: 3617455 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.2827. Min Act: -0.1700
Data Index: 3912695 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.2827. Min Act: -0.1700
Data Index: 2186064 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.2202. Min Act: -0.1700
Data Index: 7090517 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.2202. Min Act: -0.1700
Data Index: 2796228 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.2514. Min Act: -0.1700
Data Index: 6083092 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.2202. Min Act: -0.1700
Data Index: 4983678 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.1889. Min Act: -0.1700
Data Index: 7421921 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.1889. Min Act: -0.1700
Data Index: 1264612 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.1889. Min Act: -0.1700
Data Index: 5389181 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.1577. Min Act: -0.1700
Data Index: 4589674 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7202. Min Range: -6.7202
Max Act: 6.1577. Min Act: -0.1700
Data Index: 4571595 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19