Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3936 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.8728. Min Act: -0.1700
Data Index: 7777325 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.5290. Min Act: -0.1700
Data Index: 5623652 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.4665. Min Act: -0.1700
Data Index: 1108938 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.4040. Min Act: -0.1700
Data Index: 1425835 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.3415. Min Act: -0.1700
Data Index: 7455578 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.3103. Min Act: -0.1700
Data Index: 8815629 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.2790. Min Act: -0.1700
Data Index: 5497112 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.2478. Min Act: -0.1700
Data Index: 1528228 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.2478. Min Act: -0.1700
Data Index: 5343451 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.2165. Min Act: -0.1700
Data Index: 7897906 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.2165. Min Act: -0.1700
Data Index: 3511012 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.1540. Min Act: -0.1700
Data Index: 2351860 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.1853. Min Act: -0.1700
Data Index: 6752135 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.1853. Min Act: -0.1700
Data Index: 8213139 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.1540. Min Act: -0.1700
Data Index: 8745225 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.1540. Min Act: -0.1700
Data Index: 5650283 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.1228. Min Act: -0.1700
Data Index: 3511527 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.1228. Min Act: -0.1700
Data Index: 277757 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.0915. Min Act: -0.1700
Data Index: 4234933 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8728. Min Range: -5.8728
Max Act: 5.1228. Min Act: -0.1700
Data Index: 7998852 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19