Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.4269. Min Act: -0.1700
Data Index: 612341 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.4269. Min Act: -0.1700
Data Index: 2208193 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.3642. Min Act: -0.1700
Data Index: 7643136 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.3642. Min Act: -0.1700
Data Index: 2271205 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.3328. Min Act: -0.1700
Data Index: 7492756 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.3328. Min Act: -0.1700
Data Index: 7757515 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.3328. Min Act: -0.1700
Data Index: 5414266 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2858. Min Act: -0.1700
Data Index: 7653942 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2543. Min Act: -0.1700
Data Index: 291174 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2543. Min Act: -0.1700
Data Index: 6754333 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2543. Min Act: -0.1700
Data Index: 4180407 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2543. Min Act: -0.1700
Data Index: 5808572 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2543. Min Act: -0.1700
Data Index: 6020389 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2386. Min Act: -0.1700
Data Index: 8487080 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2386. Min Act: -0.1700
Data Index: 8580327 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2386. Min Act: -0.1700
Data Index: 1600690 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2229. Min Act: -0.1700
Data Index: 1068718 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2229. Min Act: -0.1700
Data Index: 3967771 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2229. Min Act: -0.1700
Data Index: 3945672 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4269. Min Range: -3.4269
Max Act: 3.2386. Min Act: -0.1700
Data Index: 1191762 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19