Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3162 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.8817. Min Act: -0.1700
Data Index: 1683072 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.7567. Min Act: -0.1700
Data Index: 6678163 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.5380. Min Act: -0.1700
Data Index: 251519 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.3505. Min Act: -0.1700
Data Index: 7992735 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 3076591 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 6266301 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.2880. Min Act: -0.1700
Data Index: 899755 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.2880. Min Act: -0.1700
Data Index: 1411809 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.2880. Min Act: -0.1700
Data Index: 3096102 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 3239333 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.2567. Min Act: -0.1700
Data Index: 4135567 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 1277948 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 6064770 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.2254. Min Act: -0.1700
Data Index: 6849592 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.1942. Min Act: -0.1700
Data Index: 6208818 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.1942. Min Act: -0.1700
Data Index: 2786399 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.1942. Min Act: -0.1700
Data Index: 397068 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.1942. Min Act: -0.1700
Data Index: 3906000 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.1942. Min Act: -0.1700
Data Index: 7447031 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8817. Min Range: -4.8817
Max Act: 4.1629. Min Act: -0.1700
Data Index: 6041679 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19