Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1707 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.3195. Min Act: -0.1700
Data Index: 1874970 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.3195. Min Act: -0.1700
Data Index: 5776144 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.2570. Min Act: -0.1700
Data Index: 7800935 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.1632. Min Act: -0.1700
Data Index: 4564910 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.1320. Min Act: -0.1700
Data Index: 3095122 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.1007. Min Act: -0.1700
Data Index: 1219120 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.1007. Min Act: -0.1700
Data Index: 6109462 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.0695. Min Act: -0.1700
Data Index: 4158349 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.0695. Min Act: -0.1700
Data Index: 2758347 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.0695. Min Act: -0.1700
Data Index: 3797743 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.0695. Min Act: -0.1700
Data Index: 3670347 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.0070. Min Act: -0.1700
Data Index: 3634077 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3195. Min Range: -5.3195
Max Act: 5.0070. Min Act: -0.1700
Data Index: 34265 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3195. Min Range: -5.3195
Max Act: 4.9757. Min Act: -0.1700
Data Index: 2695017 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3195. Min Range: -5.3195
Max Act: 4.9757. Min Act: -0.1700
Data Index: 4661802 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3195. Min Range: -5.3195
Max Act: 4.9757. Min Act: -0.1700
Data Index: 529987 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3195. Min Range: -5.3195
Max Act: 4.9445. Min Act: -0.1700
Data Index: 4893582 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3195. Min Range: -5.3195
Max Act: 4.9445. Min Act: -0.1700
Data Index: 623829 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3195. Min Range: -5.3195
Max Act: 4.9132. Min Act: -0.1700
Data Index: 582249 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3195. Min Range: -5.3195
Max Act: 4.9445. Min Act: -0.1700
Data Index: 5578756 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19