Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4194. Min Range: -9.4194
Max Act: 9.4194. Min Act: -0.1700
Data Index: 2344401 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4194. Min Range: -9.4194
Max Act: 9.2944. Min Act: -0.1700
Data Index: 2746548 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4194. Min Range: -9.4194
Max Act: 9.2319. Min Act: -0.1700
Data Index: 6837453 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4194. Min Range: -9.4194
Max Act: 9.1694. Min Act: -0.1700
Data Index: 4495786 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4194. Min Range: -9.4194
Max Act: 9.1069. Min Act: -0.1700
Data Index: 4024121 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4194. Min Range: -9.4194
Max Act: 9.0444. Min Act: -0.1700
Data Index: 7059652 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.9819. Min Act: -0.1700
Data Index: 7046182 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.9819. Min Act: -0.1700
Data Index: 8012948 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.9819. Min Act: -0.1700
Data Index: 3206689 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.9194. Min Act: -0.1700
Data Index: 6964046 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.9194. Min Act: -0.1700
Data Index: 1446581 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.8569. Min Act: -0.1700
Data Index: 2504480 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.7944. Min Act: -0.1700
Data Index: 62706 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.7944. Min Act: -0.1700
Data Index: 2174180 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.7944. Min Act: -0.1700
Data Index: 1931230 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.7944. Min Act: -0.1700
Data Index: 8823657 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.7944. Min Act: -0.1700
Data Index: 1777940 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.7319. Min Act: -0.1700
Data Index: 1379878 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.7319. Min Act: -0.1700
Data Index: 5154202 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4194. Min Range: -9.4194
Max Act: 8.7319. Min Act: -0.1700
Data Index: 7481691 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19