Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4140 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.4652. Min Act: -0.1700
Data Index: 6876037 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.3402. Min Act: -0.1700
Data Index: 2818648 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.2152. Min Act: -0.1700
Data Index: 4135184 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.1839. Min Act: -0.1700
Data Index: 7689059 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.1527. Min Act: -0.1700
Data Index: 6846369 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.1214. Min Act: -0.1700
Data Index: 8286259 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.0902. Min Act: -0.1700
Data Index: 1815696 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.0902. Min Act: -0.1700
Data Index: 1193729 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.0589. Min Act: -0.1700
Data Index: 3195815 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.0589. Min Act: -0.1700
Data Index: 1322019 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.0589. Min Act: -0.1700
Data Index: 6213309 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.0589. Min Act: -0.1700
Data Index: 1299355 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.0277. Min Act: -0.1700
Data Index: 4790930 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4652. Min Range: -8.4652
Max Act: 8.0277. Min Act: -0.1700
Data Index: 2403854 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4652. Min Range: -8.4652
Max Act: 7.9964. Min Act: -0.1700
Data Index: 4997836 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4652. Min Range: -8.4652
Max Act: 7.9964. Min Act: -0.1700
Data Index: 4997835 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4652. Min Range: -8.4652
Max Act: 7.9964. Min Act: -0.1700
Data Index: 1023215 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4652. Min Range: -8.4652
Max Act: 7.9652. Min Act: -0.1700
Data Index: 5436273 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4652. Min Range: -8.4652
Max Act: 7.9339. Min Act: -0.1700
Data Index: 964806 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4652. Min Range: -8.4652
Max Act: 7.9652. Min Act: -0.1700
Data Index: 8217058 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19