Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.7416. Min Act: -0.1700
Data Index: 8779500 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.6791. Min Act: -0.1700
Data Index: 3602614 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.6166. Min Act: -0.1700
Data Index: 6020572 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.6166. Min Act: -0.1700
Data Index: 7924347 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.4916. Min Act: -0.1700
Data Index: 2734355 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.4916. Min Act: -0.1700
Data Index: 7619283 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.4291. Min Act: -0.1700
Data Index: 118321 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.4916. Min Act: -0.1700
Data Index: 5778829 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.3041. Min Act: -0.1700
Data Index: 5668914 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.3041. Min Act: -0.1700
Data Index: 6253568 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.3041. Min Act: -0.1700
Data Index: 7091817 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.3041. Min Act: -0.1700
Data Index: 7216588 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.3041. Min Act: -0.1700
Data Index: 663334 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.2416. Min Act: -0.1700
Data Index: 5627994 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.2416. Min Act: -0.1700
Data Index: 1488439 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.2416. Min Act: -0.1700
Data Index: 193068 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.2416. Min Act: -0.1700
Data Index: 3817517 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.1791. Min Act: -0.1700
Data Index: 3051908 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.1166. Min Act: -0.1700
Data Index: 4679997 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7416. Min Range: -8.7416
Max Act: 8.1791. Min Act: -0.1700
Data Index: 823653 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19