Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.4193. Min Act: -0.1700
Data Index: 6341170 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.2718. Min Act: -0.1700
Data Index: 727962 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.2718. Min Act: -0.1700
Data Index: 3155570 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.2553. Min Act: -0.1696
Data Index: 3258593 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.2718. Min Act: -0.1700
Data Index: 3401152 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.2222. Min Act: -0.1700
Data Index: 1805976 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1890. Min Act: -0.1700
Data Index: 3824650 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1724. Min Act: -0.1700
Data Index: 554775 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1557. Min Act: -0.1700
Data Index: 6565117 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1724. Min Act: -0.1700
Data Index: 739019 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1724. Min Act: -0.1700
Data Index: 5756764 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1724. Min Act: -0.1700
Data Index: 2054020 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1724. Min Act: -0.1700
Data Index: 3574943 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1557. Min Act: -0.1700
Data Index: 5952516 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1724. Min Act: -0.1700
Data Index: 1269171 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1557. Min Act: -0.1700
Data Index: 1805977 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1557. Min Act: -0.1700
Data Index: 2461050 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1224. Min Act: -0.1700
Data Index: 5852354 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1391. Min Act: -0.1700
Data Index: 8811351 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4193. Min Range: -2.4193
Max Act: 2.1224. Min Act: -0.1699
Data Index: 296764 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19