Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.6194. Min Act: -0.1700
Data Index: 152834 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.6194. Min Act: -0.1700
Data Index: 8588446 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.5569. Min Act: -0.1700
Data Index: 5485359 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.4944. Min Act: -0.1700
Data Index: 2822948 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.4319. Min Act: -0.1700
Data Index: 4051156 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.4319. Min Act: -0.1700
Data Index: 3079269 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.4006. Min Act: -0.1700
Data Index: 8707157 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.4006. Min Act: -0.1700
Data Index: 4953112 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.3069. Min Act: -0.1700
Data Index: 3508968 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.2756. Min Act: -0.1700
Data Index: 7206039 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.2756. Min Act: -0.1700
Data Index: 8575102 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.2756. Min Act: -0.1700
Data Index: 4311839 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.2444. Min Act: -0.1700
Data Index: 3833777 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.2131. Min Act: -0.1700
Data Index: 84784 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.1819. Min Act: -0.1700
Data Index: 229341 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.2131. Min Act: -0.1700
Data Index: 4359901 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.1819. Min Act: -0.1700
Data Index: 6870749 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.2131. Min Act: -0.1700
Data Index: 3696950 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.1194. Min Act: -0.1700
Data Index: 4845226 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6194. Min Range: -6.6194
Max Act: 6.1506. Min Act: -0.1700
Data Index: 7548709 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19