Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5904 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.8088. Min Act: -0.1700
Data Index: 5427319 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.6838. Min Act: -0.1700
Data Index: 2801960 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.4650. Min Act: -0.1700
Data Index: 3615498 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.4338. Min Act: -0.1700
Data Index: 1314697 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.3400. Min Act: -0.1700
Data Index: 3058641 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.3088. Min Act: -0.1700
Data Index: 2856659 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.3400. Min Act: -0.1700
Data Index: 4376525 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.3088. Min Act: -0.1700
Data Index: 7955531 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.3400. Min Act: -0.1700
Data Index: 1082695 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.3088. Min Act: -0.1700
Data Index: 7783026 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.3088. Min Act: -0.1700
Data Index: 4882144 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2775. Min Act: -0.1700
Data Index: 753172 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2463. Min Act: -0.1700
Data Index: 4879595 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2775. Min Act: -0.1700
Data Index: 8659739 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2463. Min Act: -0.1700
Data Index: 4007284 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2775. Min Act: -0.1700
Data Index: 6178492 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2150. Min Act: -0.1700
Data Index: 710433 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2150. Min Act: -0.1700
Data Index: 4795576 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2150. Min Act: -0.1700
Data Index: 144220 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8088. Min Range: -4.8088
Max Act: 4.2150. Min Act: -0.1700
Data Index: 4085404 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19