Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.8228. Min Act: -0.1700
Data Index: 8069763 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.5098. Min Act: -0.1700
Data Index: 606393 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.5098. Min Act: -0.1700
Data Index: 7139058 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.5411. Min Act: -0.1700
Data Index: 5398382 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.4785. Min Act: -0.1700
Data Index: 2266716 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.4785. Min Act: -0.1700
Data Index: 7166565 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3845. Min Act: -0.1700
Data Index: 7055975 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.4628. Min Act: -0.1700
Data Index: 1230747 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.4472. Min Act: -0.1700
Data Index: 4719216 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3688. Min Act: -0.1700
Data Index: 4163451 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3531. Min Act: -0.1700
Data Index: 3225611 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.4158. Min Act: -0.1700
Data Index: 2442684 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3688. Min Act: -0.1700
Data Index: 6971034 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3688. Min Act: -0.1700
Data Index: 6444573 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3688. Min Act: -0.1700
Data Index: 8363465 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3060. Min Act: -0.1700
Data Index: 4231310 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3060. Min Act: -0.1700
Data Index: 5495398 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3374. Min Act: -0.1700
Data Index: 4738918 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3845. Min Act: -0.1700
Data Index: 8304592 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8228. Min Range: -3.8228
Max Act: 3.3531. Min Act: -0.1700
Data Index: 3924764 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19