Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 804 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.5936. Min Act: -0.1700
Data Index: 7506192 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.5311. Min Act: -0.1700
Data Index: 7882121 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.4686. Min Act: -0.1700
Data Index: 4151835 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.3748. Min Act: -0.1700
Data Index: 8403943 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.3748. Min Act: -0.1700
Data Index: 2596010 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.3436. Min Act: -0.1700
Data Index: 8724957 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.3436. Min Act: -0.1700
Data Index: 3845215 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.3123. Min Act: -0.1700
Data Index: 7601090 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.3123. Min Act: -0.1700
Data Index: 1126526 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.2811. Min Act: -0.1700
Data Index: 1917716 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.2811. Min Act: -0.1700
Data Index: 3840358 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.2811. Min Act: -0.1700
Data Index: 765386 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.2811. Min Act: -0.1700
Data Index: 1373190 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.2498. Min Act: -0.1700
Data Index: 4040066 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.1873. Min Act: -0.1700
Data Index: 307541 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.1873. Min Act: -0.1700
Data Index: 7367734 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.1873. Min Act: -0.1700
Data Index: 306518 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.1561. Min Act: -0.1700
Data Index: 1739031 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.1561. Min Act: -0.1700
Data Index: 6315299 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5936. Min Range: -5.5936
Max Act: 5.0936. Min Act: -0.1700
Data Index: 1095534 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19