Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0133. Min Range: -6.0133
Max Act: 6.0133. Min Act: -0.1700
Data Index: 1087332 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.9195. Min Act: -0.1700
Data Index: 8157692 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.8570. Min Act: -0.1700
Data Index: 7806785 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.6070. Min Act: -0.1700
Data Index: 6188457 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.5758. Min Act: -0.1700
Data Index: 297897 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.5758. Min Act: -0.1700
Data Index: 8089451 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.5133. Min Act: -0.1700
Data Index: 6624398 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.4820. Min Act: -0.1699
Data Index: 4567234 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.4508. Min Act: -0.1700
Data Index: 3238978 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.4508. Min Act: -0.1700
Data Index: 592325 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3570. Min Act: -0.1700
Data Index: 7917578 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3570. Min Act: -0.1700
Data Index: 6857161 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3258. Min Act: -0.1700
Data Index: 1081292 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3258. Min Act: -0.1700
Data Index: 1178378 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.2633. Min Act: -0.1700
Data Index: 7226318 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.2633. Min Act: -0.1700
Data Index: 5911676 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.2320. Min Act: -0.1700
Data Index: 2872240 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.2320. Min Act: -0.1700
Data Index: 4829712 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.1695. Min Act: -0.1700
Data Index: 7110278 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.2320. Min Act: -0.1693
Data Index: 1276687 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19