Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1205 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3690. Min Range: -8.3690
Max Act: 8.3690. Min Act: -0.1700
Data Index: 4073598 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3690. Min Range: -8.3690
Max Act: 8.1190. Min Act: -0.1700
Data Index: 1072261 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3690. Min Range: -8.3690
Max Act: 8.0565. Min Act: -0.1700
Data Index: 6487446 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.9315. Min Act: -0.1700
Data Index: 4020221 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.8690. Min Act: -0.1700
Data Index: 984909 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.8690. Min Act: -0.1700
Data Index: 3824989 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.8690. Min Act: -0.1700
Data Index: 551471 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.8065. Min Act: -0.1700
Data Index: 5745688 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.8065. Min Act: -0.1700
Data Index: 5981840 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.8065. Min Act: -0.1700
Data Index: 4221884 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.8065. Min Act: -0.1700
Data Index: 7443345 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.7440. Min Act: -0.1700
Data Index: 2330826 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.6815. Min Act: -0.1700
Data Index: 385643 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.6503. Min Act: -0.1700
Data Index: 5175933 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.6503. Min Act: -0.1700
Data Index: 6906511 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.6503. Min Act: -0.1700
Data Index: 4893827 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.6190. Min Act: -0.1700
Data Index: 102194 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.6190. Min Act: -0.1700
Data Index: 4793257 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.5878. Min Act: -0.1700
Data Index: 1727687 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3690. Min Range: -8.3690
Max Act: 7.5253. Min Act: -0.1700
Data Index: 8271298 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19