Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.1185. Min Act: -0.1700
Data Index: 7366868 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0872. Min Act: -0.1700
Data Index: 4337075 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0560. Min Act: -0.1700
Data Index: 2163791 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0560. Min Act: -0.1700
Data Index: 2478233 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0247. Min Act: -0.1700
Data Index: 5234107 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0247. Min Act: -0.1700
Data Index: 7432101 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0247. Min Act: -0.1700
Data Index: 8605250 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0560. Min Act: -0.1700
Data Index: 6232101 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1185. Min Range: -5.1185
Max Act: 5.0247. Min Act: -0.1700
Data Index: 2798978 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9935. Min Act: -0.1700
Data Index: 6894754 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9622. Min Act: -0.1700
Data Index: 6850120 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9935. Min Act: -0.1700
Data Index: 314462 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9310. Min Act: -0.1700
Data Index: 2973454 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9310. Min Act: -0.1700
Data Index: 344616 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9310. Min Act: -0.1700
Data Index: 6611358 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9310. Min Act: -0.1700
Data Index: 5096741 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9310. Min Act: -0.1700
Data Index: 1071593 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.9622. Min Act: -0.1700
Data Index: 5166568 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.8685. Min Act: -0.1700
Data Index: 2346404 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1185. Min Range: -5.1185
Max Act: 4.8997. Min Act: -0.1700
Data Index: 5890148 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19