Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1532 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1450. Min Range: -8.1450
Max Act: 8.0825. Min Act: -0.1700
Data Index: 1854350 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1450. Min Range: -8.1450
Max Act: 8.0825. Min Act: -0.1700
Data Index: 8289608 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1450. Min Range: -8.1450
Max Act: 8.0825. Min Act: -0.1700
Data Index: 3981252 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1450. Min Range: -8.1450
Max Act: 8.1450. Min Act: -0.1700
Data Index: 3981254 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.9575. Min Act: -0.1700
Data Index: 5638095 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.8637. Min Act: -0.1700
Data Index: 2776090 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.8637. Min Act: -0.1700
Data Index: 7911933 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.6762. Min Act: -0.1700
Data Index: 2437208 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.3637. Min Act: -0.1700
Data Index: 8614292 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.3637. Min Act: -0.1700
Data Index: 7310638 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.3012. Min Act: -0.1700
Data Index: 5026529 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.3325. Min Act: -0.1700
Data Index: 723865 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.2700. Min Act: -0.1700
Data Index: 4080723 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.1762. Min Act: -0.1700
Data Index: 5290130 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.1137. Min Act: -0.1700
Data Index: 6840485 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.1450. Min Act: -0.1700
Data Index: 2461355 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.1762. Min Act: -0.1700
Data Index: 5042219 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.1762. Min Act: -0.1700
Data Index: 6770744 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.1450. Min Act: -0.1700
Data Index: 4991733 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1450. Min Range: -8.1450
Max Act: 7.1137. Min Act: -0.1700
Data Index: 6600482 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19