Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.8756. Min Act: -0.1700
Data Index: 412203 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.9069. Min Act: -0.1700
Data Index: 6750194 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.8756. Min Act: -0.1700
Data Index: 7192584 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.3756. Min Act: -0.1700
Data Index: 2849547 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.3444. Min Act: -0.1700
Data Index: 4265973 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.3131. Min Act: -0.1700
Data Index: 28638 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.3131. Min Act: -0.1700
Data Index: 2163636 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.3131. Min Act: -0.1700
Data Index: 1727096 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.2819. Min Act: -0.1700
Data Index: 4331316 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.2819. Min Act: -0.1700
Data Index: 4954212 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.2506. Min Act: -0.1700
Data Index: 4411377 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.2194. Min Act: -0.1700
Data Index: 4323780 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.2194. Min Act: -0.1700
Data Index: 6329206 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.1569. Min Act: -0.1700
Data Index: 2780641 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.1256. Min Act: -0.1700
Data Index: 7861414 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.1256. Min Act: -0.1700
Data Index: 8145514 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.0944. Min Act: -0.1700
Data Index: 4265977 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.1256. Min Act: -0.1700
Data Index: 8389431 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.0944. Min Act: -0.1700
Data Index: 5765791 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9069. Min Range: -6.9069
Max Act: 6.0944. Min Act: -0.1700
Data Index: 2570483 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19