Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4756 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.8927. Min Act: -0.1700
Data Index: 8229979 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.7677. Min Act: -0.1700
Data Index: 7532870 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.7052. Min Act: -0.1700
Data Index: 2638799 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.7052. Min Act: -0.1700
Data Index: 3349136 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.5802. Min Act: -0.1700
Data Index: 8477675 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.5177. Min Act: -0.1700
Data Index: 6016524 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.4552. Min Act: -0.1700
Data Index: 8784979 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.4552. Min Act: -0.1700
Data Index: 7502159 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.5177. Min Act: -0.1700
Data Index: 8477672 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.4552. Min Act: -0.1700
Data Index: 7658772 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.3927. Min Act: -0.1700
Data Index: 8477676 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.3927. Min Act: -0.1700
Data Index: 310471 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.3302. Min Act: -0.1700
Data Index: 2688767 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.3302. Min Act: -0.1700
Data Index: 1247700 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.3302. Min Act: -0.1700
Data Index: 2780335 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.3302. Min Act: -0.1700
Data Index: 6107134 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.3302. Min Act: -0.1700
Data Index: 6898827 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.2677. Min Act: -0.1700
Data Index: 6712166 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.2677. Min Act: -0.1700
Data Index: 576105 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8927. Min Range: -9.8927
Max Act: 9.2677. Min Act: -0.1700
Data Index: 3915574 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19