Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.2210. Min Act: -0.1700
Data Index: 4586260 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0960. Min Act: -0.1700
Data Index: 3126455 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0960. Min Act: -0.1700
Data Index: 1195101 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0648. Min Act: -0.1700
Data Index: 2164798 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0335. Min Act: -0.1700
Data Index: 5967984 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0335. Min Act: -0.1700
Data Index: 8104904 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0335. Min Act: -0.1700
Data Index: 6915669 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0335. Min Act: -0.1700
Data Index: 5729953 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0023. Min Act: -0.1700
Data Index: 7903631 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0023. Min Act: -0.1700
Data Index: 986250 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2210. Min Range: -5.2210
Max Act: 5.0023. Min Act: -0.1700
Data Index: 7195620 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9710. Min Act: -0.1700
Data Index: 5651665 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9710. Min Act: -0.1700
Data Index: 826965 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9398. Min Act: -0.1700
Data Index: 2967256 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9398. Min Act: -0.1700
Data Index: 6570976 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9398. Min Act: -0.1700
Data Index: 5162363 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9398. Min Act: -0.1700
Data Index: 114613 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9085. Min Act: -0.1700
Data Index: 139990 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9085. Min Act: -0.1700
Data Index: 3328978 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2210. Min Range: -5.2210
Max Act: 4.9085. Min Act: -0.1700
Data Index: 1259088 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19