Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.7547. Min Act: -0.1700
Data Index: 7166071 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.7547. Min Act: -0.1700
Data Index: 2452986 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.7235. Min Act: -0.1700
Data Index: 2987108 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.6609. Min Act: -0.1700
Data Index: 6045652 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.6609. Min Act: -0.1700
Data Index: 6870491 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.6296. Min Act: -0.1700
Data Index: 6686543 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.6296. Min Act: -0.1700
Data Index: 4907898 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.6296. Min Act: -0.1700
Data Index: 2960388 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.6296. Min Act: -0.1700
Data Index: 272999 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.6296. Min Act: -0.1700
Data Index: 7805195 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 1759335 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 3171036 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 5324361 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 8179738 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 5144338 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 7977275 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 7471972 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 6322715 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5983. Min Act: -0.1700
Data Index: 195337 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7547. Min Range: -3.7547
Max Act: 3.5670. Min Act: -0.1700
Data Index: 2482505 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19