Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.9893. Min Act: -0.1700
Data Index: 6474998 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.8643. Min Act: -0.1700
Data Index: 674313 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.8331. Min Act: -0.1700
Data Index: 5892375 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.8331. Min Act: -0.1700
Data Index: 1507512 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.8018. Min Act: -0.1700
Data Index: 7298531 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.7706. Min Act: -0.1700
Data Index: 4822334 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.7706. Min Act: -0.1700
Data Index: 2678053 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.7393. Min Act: -0.1700
Data Index: 3821528 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.7081. Min Act: -0.1700
Data Index: 4641793 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.7081. Min Act: -0.1700
Data Index: 3683180 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.7081. Min Act: -0.1700
Data Index: 3604039 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.7081. Min Act: -0.1700
Data Index: 8356511 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.6768. Min Act: -0.1700
Data Index: 3177547 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.6768. Min Act: -0.1700
Data Index: 8441880 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.6768. Min Act: -0.1700
Data Index: 263690 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.6768. Min Act: -0.1700
Data Index: 6022674 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.6456. Min Act: -0.1700
Data Index: 2389115 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.6456. Min Act: -0.1700
Data Index: 41563 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.6143. Min Act: -0.1700
Data Index: 588903 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9893. Min Range: -4.9893
Max Act: 4.6456. Min Act: -0.1700
Data Index: 2163038 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19