Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.4990. Min Act: -0.1700
Data Index: 7997201 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.4365. Min Act: -0.1700
Data Index: 4628542 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.3740. Min Act: -0.1700
Data Index: 8095293 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.3740. Min Act: -0.1700
Data Index: 2134933 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.3427. Min Act: -0.1700
Data Index: 3508124 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.3115. Min Act: -0.1700
Data Index: 4963708 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.3115. Min Act: -0.1700
Data Index: 8266665 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.3427. Min Act: -0.1700
Data Index: 894062 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2802. Min Act: -0.1700
Data Index: 978840 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2802. Min Act: -0.1700
Data Index: 5944056 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2490. Min Act: -0.1700
Data Index: 6170617 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2490. Min Act: -0.1700
Data Index: 1535935 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2490. Min Act: -0.1700
Data Index: 1888925 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2490. Min Act: -0.1700
Data Index: 1149526 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2490. Min Act: -0.1700
Data Index: 1475944 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2490. Min Act: -0.1700
Data Index: 8434938 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2177. Min Act: -0.1700
Data Index: 5738234 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2802. Min Act: -0.1700
Data Index: 6705206 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2177. Min Act: -0.1700
Data Index: 785539 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4990. Min Range: -4.4990
Max Act: 4.2177. Min Act: -0.1700
Data Index: 5738235 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19