Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5802 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.8275. Min Act: -0.1700
Data Index: 6211471 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.8275. Min Act: -0.1700
Data Index: 2372371 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.7337. Min Act: -0.1700
Data Index: 6749335 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.7024. Min Act: -0.1700
Data Index: 7582827 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.7024. Min Act: -0.1700
Data Index: 2836068 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.7337. Min Act: -0.1700
Data Index: 3423190 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6867. Min Act: -0.1700
Data Index: 7056950 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6867. Min Act: -0.1700
Data Index: 7561627 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6867. Min Act: -0.1700
Data Index: 2653124 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6711. Min Act: -0.1700
Data Index: 2471546 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6554. Min Act: -0.1700
Data Index: 2795929 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6554. Min Act: -0.1700
Data Index: 6427765 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6554. Min Act: -0.1700
Data Index: 1736883 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6242. Min Act: -0.1700
Data Index: 1444743 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6242. Min Act: -0.1700
Data Index: 7666211 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6085. Min Act: -0.1700
Data Index: 6226360 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6242. Min Act: -0.1700
Data Index: 7883180 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6085. Min Act: -0.1700
Data Index: 6227693 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.5929. Min Act: -0.1700
Data Index: 6353478 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8275. Min Range: -3.8275
Max Act: 3.6085. Min Act: -0.1700
Data Index: 632806 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19