Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4502 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.9518. Min Act: -0.1700
Data Index: 2756896 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.8581. Min Act: -0.1700
Data Index: 8609491 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.7331. Min Act: -0.1700
Data Index: 1495694 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.6706. Min Act: -0.1700
Data Index: 7708318 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.5456. Min Act: -0.1700
Data Index: 4090599 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.4206. Min Act: -0.1700
Data Index: 6846628 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.3268. Min Act: -0.1700
Data Index: 3810245 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.3268. Min Act: -0.1700
Data Index: 6124464 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2956. Min Act: -0.1700
Data Index: 8381678 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.3268. Min Act: -0.1700
Data Index: 8096017 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2643. Min Act: -0.1700
Data Index: 5989569 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2643. Min Act: -0.1700
Data Index: 934595 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2643. Min Act: -0.1700
Data Index: 7823859 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2331. Min Act: -0.1700
Data Index: 4066638 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2331. Min Act: -0.1700
Data Index: 1184848 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2331. Min Act: -0.1700
Data Index: 6650870 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2018. Min Act: -0.1700
Data Index: 3682478 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2018. Min Act: -0.1700
Data Index: 6309044 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.2018. Min Act: -0.1700
Data Index: 8002414 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9518. Min Range: -5.9518
Max Act: 5.1706. Min Act: -0.1700
Data Index: 4817653 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19