Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.9316. Min Act: -0.1700
Data Index: 4885424 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.8691. Min Act: -0.1700
Data Index: 1081394 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.8378. Min Act: -0.1700
Data Index: 5311512 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.8378. Min Act: -0.1700
Data Index: 4288064 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.8066. Min Act: -0.1700
Data Index: 4100222 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.8066. Min Act: -0.1700
Data Index: 3113512 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.7753. Min Act: -0.1700
Data Index: 6064669 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.7441. Min Act: -0.1700
Data Index: 5035600 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.7441. Min Act: -0.1700
Data Index: 5940227 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.7441. Min Act: -0.1700
Data Index: 555409 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.7441. Min Act: -0.1700
Data Index: 879362 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.7441. Min Act: -0.1700
Data Index: 6202380 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.6503. Min Act: -0.1700
Data Index: 320856 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.6816. Min Act: -0.1700
Data Index: 1462521 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.6503. Min Act: -0.1700
Data Index: 7423778 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.6816. Min Act: -0.1700
Data Index: 2974770 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.6816. Min Act: -0.1700
Data Index: 2770030 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.6816. Min Act: -0.1700
Data Index: 981122 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.6191. Min Act: -0.1700
Data Index: 4306495 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9316. Min Range: -5.9316
Max Act: 5.6503. Min Act: -0.1700
Data Index: 1566294 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19