Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4834 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.2304. Min Act: -0.1700
Data Index: 1191808 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1366. Min Act: -0.1700
Data Index: 5137546 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1054. Min Act: -0.1700
Data Index: 1490501 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0429. Min Act: -0.1700
Data Index: 1490465 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 1272407 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9803. Min Act: -0.1700
Data Index: 8253489 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9803. Min Act: -0.1700
Data Index: 1490467 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9803. Min Act: -0.1700
Data Index: 1490466 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9491. Min Act: -0.1700
Data Index: 8731941 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9178. Min Act: -0.1700
Data Index: 677961 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9491. Min Act: -0.1700
Data Index: 7292383 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9178. Min Act: -0.1700
Data Index: 2064476 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9491. Min Act: -0.1700
Data Index: 8815152 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9491. Min Act: -0.1700
Data Index: 6536953 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.9178. Min Act: -0.1700
Data Index: 6040319 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.8866. Min Act: -0.1700
Data Index: 5106666 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.8866. Min Act: -0.1700
Data Index: 4267029 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.8866. Min Act: -0.1700
Data Index: 2817286 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.8553. Min Act: -0.1700
Data Index: 8552853 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2304. Min Range: -4.2304
Max Act: 3.8553. Min Act: -0.1700
Data Index: 1457404 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19