Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.5893. Min Act: -0.1700
Data Index: 1883601 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.5580. Min Act: -0.1700
Data Index: 3189160 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.5268. Min Act: -0.1700
Data Index: 364128 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.5268. Min Act: -0.1700
Data Index: 7186572 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4643. Min Act: -0.1700
Data Index: 8745699 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4643. Min Act: -0.1700
Data Index: 5826971 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4330. Min Act: -0.1700
Data Index: 2102472 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4330. Min Act: -0.1700
Data Index: 3237286 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 6467948 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 3435487 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 5363442 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 4118446 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.4018. Min Act: -0.1700
Data Index: 4096475 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 8126367 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 1041382 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 8460175 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 5177108 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 8729213 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 238456 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5893. Min Range: -5.5893
Max Act: 5.3705. Min Act: -0.1700
Data Index: 3311554 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19