Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.2907. Min Act: -0.1700
Data Index: 2980809 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.2282. Min Act: -0.1700
Data Index: 8542170 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.2282. Min Act: -0.1700
Data Index: 2107451 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.2282. Min Act: -0.1700
Data Index: 118091 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1657. Min Act: -0.1700
Data Index: 2980804 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1657. Min Act: -0.1700
Data Index: 305627 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1345. Min Act: -0.1700
Data Index: 4647685 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1345. Min Act: -0.1700
Data Index: 5300961 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1345. Min Act: -0.1700
Data Index: 1661769 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1345. Min Act: -0.1700
Data Index: 5300962 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1657. Min Act: -0.1700
Data Index: 7322698 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1345. Min Act: -0.1700
Data Index: 6633064 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1345. Min Act: -0.1700
Data Index: 6451291 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1345. Min Act: -0.1700
Data Index: 1826155 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1345. Min Act: -0.1700
Data Index: 5968768 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1032. Min Act: -0.1700
Data Index: 6110598 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.0719. Min Act: -0.1700
Data Index: 7239760 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.0407. Min Act: -0.1700
Data Index: 50786 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.0719. Min Act: -0.1700
Data Index: 2185218 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2907. Min Range: -4.2907
Max Act: 4.1032. Min Act: -0.1700
Data Index: 5071512 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19