Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0402. Min Range: -6.0402
Max Act: 6.0402. Min Act: -0.1700
Data Index: 5170190 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0402. Min Range: -6.0402
Max Act: 6.0090. Min Act: -0.1700
Data Index: 8632656 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.9465. Min Act: -0.1700
Data Index: 4037810 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.8840. Min Act: -0.1700
Data Index: 4683625 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.7902. Min Act: -0.1700
Data Index: 7253872 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.6965. Min Act: -0.1700
Data Index: 8487233 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.6652. Min Act: -0.1700
Data Index: 7859302 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.6340. Min Act: -0.1700
Data Index: 7640472 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.6027. Min Act: -0.1700
Data Index: 2480358 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.6340. Min Act: -0.1700
Data Index: 52208 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5715. Min Act: -0.1700
Data Index: 6215564 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5715. Min Act: -0.1700
Data Index: 7067501 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5402. Min Act: -0.1700
Data Index: 4135259 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5715. Min Act: -0.1700
Data Index: 8360766 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5402. Min Act: -0.1700
Data Index: 5232124 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5090. Min Act: -0.1700
Data Index: 3061491 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5402. Min Act: -0.1700
Data Index: 7637335 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5402. Min Act: -0.1700
Data Index: 1387957 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5090. Min Act: -0.1700
Data Index: 1030281 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0402. Min Range: -6.0402
Max Act: 5.5090. Min Act: -0.1700
Data Index: 970528 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19