Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2515 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.6456. Min Act: -0.1700
Data Index: 3113462 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.4893. Min Act: -0.1700
Data Index: 4635278 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.4268. Min Act: -0.1700
Data Index: 5820885 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.3331. Min Act: -0.1700
Data Index: 4674025 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.3018. Min Act: -0.1700
Data Index: 5226238 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.3018. Min Act: -0.1700
Data Index: 8449527 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.2706. Min Act: -0.1700
Data Index: 5029145 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.2706. Min Act: -0.1700
Data Index: 933294 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.2393. Min Act: -0.1700
Data Index: 4377461 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.2081. Min Act: -0.1700
Data Index: 6924036 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.1456. Min Act: -0.1700
Data Index: 3492434 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.1456. Min Act: -0.1700
Data Index: 3288032 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.1143. Min Act: -0.1700
Data Index: 3176617 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.1143. Min Act: -0.1700
Data Index: 7331030 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.0518. Min Act: -0.1700
Data Index: 4698501 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.0518. Min Act: -0.1700
Data Index: 6491213 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.0206. Min Act: -0.1700
Data Index: 1227912 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6456. Min Range: -6.6456
Max Act: 5.9893. Min Act: -0.1700
Data Index: 4712997 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.0206. Min Act: -0.1700
Data Index: 6517987 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6456. Min Range: -6.6456
Max Act: 6.0206. Min Act: -0.1700
Data Index: 1381614 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19