Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5175 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.9865. Min Act: -0.1700
Data Index: 647864 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.8302. Min Act: -0.1700
Data Index: 7337043 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.6427. Min Act: -0.1700
Data Index: 6868904 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.5490. Min Act: -0.1700
Data Index: 6565512 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.5490. Min Act: -0.1700
Data Index: 1318848 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.5177. Min Act: -0.1700
Data Index: 1872414 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.4865. Min Act: -0.1700
Data Index: 1447268 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.3927. Min Act: -0.1700
Data Index: 5387254 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.3615. Min Act: -0.1700
Data Index: 5520551 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.3615. Min Act: -0.1700
Data Index: 8827477 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2990. Min Act: -0.1700
Data Index: 8173468 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2990. Min Act: -0.1700
Data Index: 310340 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2990. Min Act: -0.1700
Data Index: 8604741 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2677. Min Act: -0.1700
Data Index: 6345090 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2365. Min Act: -0.1700
Data Index: 2047579 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2365. Min Act: -0.1700
Data Index: 5062959 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2365. Min Act: -0.1700
Data Index: 7729182 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2052. Min Act: -0.1700
Data Index: 7125608 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.1740. Min Act: -0.1700
Data Index: 8253141 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9865. Min Range: -7.9865
Max Act: 7.2052. Min Act: -0.1700
Data Index: 6209537 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19