Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1500. Min Range: -6.1500
Max Act: 6.1500. Min Act: -0.1700
Data Index: 68253 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.9313. Min Act: -0.1700
Data Index: 3952958 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.8688. Min Act: -0.1700
Data Index: 8579534 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.8375. Min Act: -0.1700
Data Index: 8379277 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.8375. Min Act: -0.1700
Data Index: 7774460 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.8375. Min Act: -0.1700
Data Index: 13363 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.8375. Min Act: -0.1700
Data Index: 418899 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.8375. Min Act: -0.1700
Data Index: 5613230 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.8063. Min Act: -0.1700
Data Index: 3185034 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.8063. Min Act: -0.1700
Data Index: 7464003 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.7438. Min Act: -0.1700
Data Index: 6136085 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.7125. Min Act: -0.1700
Data Index: 8272230 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.7438. Min Act: -0.1700
Data Index: 7589003 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.7438. Min Act: -0.1700
Data Index: 1750134 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.7125. Min Act: -0.1700
Data Index: 7018423 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.6813. Min Act: -0.1700
Data Index: 8347213 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.6813. Min Act: -0.1700
Data Index: 4610648 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.6813. Min Act: -0.1700
Data Index: 2105421 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.6500. Min Act: -0.1700
Data Index: 3026381 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1500. Min Range: -6.1500
Max Act: 5.6500. Min Act: -0.1700
Data Index: 5006319 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19