Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1145. Min Range: -6.1145
Max Act: 6.1145. Min Act: -0.1700
Data Index: 1392560 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.9270. Min Act: -0.1700
Data Index: 6120468 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.8645. Min Act: -0.1700
Data Index: 7683198 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.8333. Min Act: -0.1700
Data Index: 1123053 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.8333. Min Act: -0.1700
Data Index: 5263957 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.8333. Min Act: -0.1700
Data Index: 2164728 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.8020. Min Act: -0.1700
Data Index: 3978657 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.7395. Min Act: -0.1700
Data Index: 1196514 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.7708. Min Act: -0.1700
Data Index: 7300251 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.7708. Min Act: -0.1700
Data Index: 7060900 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.7395. Min Act: -0.1700
Data Index: 8121748 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.6770. Min Act: -0.1700
Data Index: 6805971 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.6770. Min Act: -0.1700
Data Index: 5596922 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.6458. Min Act: -0.1700
Data Index: 6581694 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.6458. Min Act: -0.1700
Data Index: 1132284 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.6145. Min Act: -0.1700
Data Index: 7113946 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.6145. Min Act: -0.1700
Data Index: 4534323 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.6458. Min Act: -0.1700
Data Index: 5470827 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.5208. Min Act: -0.1700
Data Index: 3746904 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1145. Min Range: -6.1145
Max Act: 5.5520. Min Act: -0.1700
Data Index: 889647 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19