Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.8997. Min Act: -0.1700
Data Index: 6852416 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.7434. Min Act: -0.1700
Data Index: 588902 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.7122. Min Act: -0.1700
Data Index: 8226684 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.7122. Min Act: -0.1700
Data Index: 4659281 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.6497. Min Act: -0.1700
Data Index: 627390 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.6497. Min Act: -0.1700
Data Index: 2906016 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.6184. Min Act: -0.1700
Data Index: 8466044 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5872. Min Act: -0.1700
Data Index: 5065253 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.6497. Min Act: -0.1700
Data Index: 7671950 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.6184. Min Act: -0.1700
Data Index: 3108494 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.6184. Min Act: -0.1700
Data Index: 8290665 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5872. Min Act: -0.1700
Data Index: 7961369 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5872. Min Act: -0.1700
Data Index: 7438085 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5872. Min Act: -0.1700
Data Index: 3541270 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5872. Min Act: -0.1700
Data Index: 8663603 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5872. Min Act: -0.1700
Data Index: 8249089 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5872. Min Act: -0.1700
Data Index: 8487667 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5559. Min Act: -0.1700
Data Index: 4660767 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5559. Min Act: -0.1700
Data Index: 1266054 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8997. Min Range: -4.8997
Max Act: 4.5559. Min Act: -0.1700
Data Index: 7709086 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19