Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.5085. Min Act: -0.1700
Data Index: 353811 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.5085. Min Act: -0.1700
Data Index: 6314230 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.4460. Min Act: -0.1700
Data Index: 3343870 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.3835. Min Act: -0.1700
Data Index: 7689202 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.3210. Min Act: -0.1700
Data Index: 4871899 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.3210. Min Act: -0.1700
Data Index: 1775471 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.2585. Min Act: -0.1700
Data Index: 7378629 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.2585. Min Act: -0.1700
Data Index: 1226046 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.2585. Min Act: -0.1700
Data Index: 32841 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.2585. Min Act: -0.1700
Data Index: 2655157 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.1960. Min Act: -0.1700
Data Index: 2320727 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.1960. Min Act: -0.1700
Data Index: 7233090 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.1960. Min Act: -0.1700
Data Index: 6745667 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.1960. Min Act: -0.1700
Data Index: 8108512 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.1960. Min Act: -0.1700
Data Index: 6572392 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.1335. Min Act: -0.1700
Data Index: 6600758 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.1335. Min Act: -0.1700
Data Index: 4762025 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.0710. Min Act: -0.1700
Data Index: 8068767 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.1335. Min Act: -0.1700
Data Index: 1942417 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5085. Min Range: -11.5085
Max Act: 11.0710. Min Act: -0.1700
Data Index: 1990477 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19