Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1762 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.3053. Min Act: -0.1700
Data Index: 6588293 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.2428. Min Act: -0.1700
Data Index: 4292411 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.2115. Min Act: -0.1700
Data Index: 5791119 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1802. Min Act: -0.1700
Data Index: 3979001 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1490. Min Act: -0.1700
Data Index: 4530478 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1490. Min Act: -0.1700
Data Index: 3498827 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1177. Min Act: -0.1700
Data Index: 96260 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1177. Min Act: -0.1700
Data Index: 6714159 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1177. Min Act: -0.1700
Data Index: 444438 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1177. Min Act: -0.1700
Data Index: 8667262 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1177. Min Act: -0.1700
Data Index: 8360746 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.1177. Min Act: -0.1700
Data Index: 326226 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0865. Min Act: -0.1700
Data Index: 1323408 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0552. Min Act: -0.1700
Data Index: 4878262 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0240. Min Act: -0.1700
Data Index: 1538144 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0552. Min Act: -0.1700
Data Index: 5193443 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0240. Min Act: -0.1700
Data Index: 703104 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0240. Min Act: -0.1700
Data Index: 4489708 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0240. Min Act: -0.1700
Data Index: 922325 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3053. Min Range: -4.3053
Max Act: 4.0240. Min Act: -0.1700
Data Index: 4717759 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19