Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4601 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0413. Min Range: -5.0413
Max Act: 5.0413. Min Act: -0.1700
Data Index: 2556676 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.9476. Min Act: -0.1700
Data Index: 2339497 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.8851. Min Act: -0.1700
Data Index: 7022173 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.8226. Min Act: -0.1700
Data Index: 2662329 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7913. Min Act: -0.1700
Data Index: 4721447 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7913. Min Act: -0.1700
Data Index: 3227841 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7913. Min Act: -0.1700
Data Index: 5686266 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7913. Min Act: -0.1700
Data Index: 6195421 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7601. Min Act: -0.1700
Data Index: 5650148 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7601. Min Act: -0.1700
Data Index: 4682383 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7288. Min Act: -0.1700
Data Index: 7617938 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7288. Min Act: -0.1700
Data Index: 8055428 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.7288. Min Act: -0.1700
Data Index: 7156194 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.6976. Min Act: -0.1700
Data Index: 5172151 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.6663. Min Act: -0.1700
Data Index: 7897335 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.6663. Min Act: -0.1700
Data Index: 1841433 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.6351. Min Act: -0.1700
Data Index: 8711701 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.6351. Min Act: -0.1700
Data Index: 5456726 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.6351. Min Act: -0.1700
Data Index: 6490291 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0413. Min Range: -5.0413
Max Act: 4.6351. Min Act: -0.1700
Data Index: 3430204 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19