Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5941 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.2368. Min Act: -0.1700
Data Index: 5831562 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.2055. Min Act: -0.1700
Data Index: 7975210 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.2055. Min Act: -0.1700
Data Index: 3405310 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1743. Min Act: -0.1700
Data Index: 6166579 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1743. Min Act: -0.1700
Data Index: 4862522 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1430. Min Act: -0.1700
Data Index: 2792748 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1430. Min Act: -0.1700
Data Index: 8012467 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1430. Min Act: -0.1700
Data Index: 3861872 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1430. Min Act: -0.1700
Data Index: 4274315 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1430. Min Act: -0.1700
Data Index: 4882687 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1118. Min Act: -0.1700
Data Index: 462495 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.0805. Min Act: -0.1700
Data Index: 26124 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.0805. Min Act: -0.1700
Data Index: 5540376 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1118. Min Act: -0.1700
Data Index: 5475379 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1118. Min Act: -0.1700
Data Index: 966284 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1118. Min Act: -0.1700
Data Index: 5077400 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1430. Min Act: -0.1700
Data Index: 1522026 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1118. Min Act: -0.1700
Data Index: 3910804 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1118. Min Act: -0.1700
Data Index: 3471563 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2368. Min Range: -4.2368
Max Act: 4.1118. Min Act: -0.1700
Data Index: 1361043 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19