Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4417 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0944. Min Range: -9.0944
Max Act: 9.0944. Min Act: -0.1700
Data Index: 759792 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.8444. Min Act: -0.1700
Data Index: 3106399 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.6569. Min Act: -0.1700
Data Index: 2453342 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.5944. Min Act: -0.1700
Data Index: 4491246 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.4694. Min Act: -0.1700
Data Index: 7405456 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.4694. Min Act: -0.1700
Data Index: 1971133 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.4069. Min Act: -0.1700
Data Index: 1871830 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.4069. Min Act: -0.1700
Data Index: 1217845 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.3444. Min Act: -0.1700
Data Index: 5525076 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.3444. Min Act: -0.1700
Data Index: 3725575 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.3444. Min Act: -0.1700
Data Index: 3318264 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.3444. Min Act: -0.1700
Data Index: 6714537 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.2819. Min Act: -0.1700
Data Index: 5136860 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.2819. Min Act: -0.1700
Data Index: 8537532 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.2194. Min Act: -0.1700
Data Index: 793414 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.2194. Min Act: -0.1700
Data Index: 6876965 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.2194. Min Act: -0.1700
Data Index: 5669369 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.2194. Min Act: -0.1700
Data Index: 2796202 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.1569. Min Act: -0.1700
Data Index: 7007898 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0944. Min Range: -9.0944
Max Act: 8.0944. Min Act: -0.1700
Data Index: 2341339 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19