Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4396 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.3692. Min Act: -0.1700
Data Index: 5638561 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.3535. Min Act: -0.1700
Data Index: 2269891 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.3064. Min Act: -0.1700
Data Index: 5928055 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.2907. Min Act: -0.1700
Data Index: 4945170 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.2279. Min Act: -0.1700
Data Index: 8058639 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.2122. Min Act: -0.1700
Data Index: 310935 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.2122. Min Act: -0.1700
Data Index: 4570034 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.2122. Min Act: -0.1700
Data Index: 3542023 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.2122. Min Act: -0.1700
Data Index: 647074 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1965. Min Act: -0.1700
Data Index: 3602859 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1965. Min Act: -0.1700
Data Index: 6630866 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1807. Min Act: -0.1700
Data Index: 3752552 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1965. Min Act: -0.1700
Data Index: 1248148 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1965. Min Act: -0.1700
Data Index: 6682844 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1650. Min Act: -0.1700
Data Index: 8549926 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1493. Min Act: -0.1700
Data Index: 415582 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1335. Min Act: -0.1700
Data Index: 5084944 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1335. Min Act: -0.1700
Data Index: 4319944 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1493. Min Act: -0.1700
Data Index: 3857690 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3692. Min Range: -3.3692
Max Act: 3.1335. Min Act: -0.1700
Data Index: 3899543 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19