Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.9316. Min Act: -0.1700
Data Index: 6928966 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.9003. Min Act: -0.1700
Data Index: 1696496 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.8066. Min Act: -0.1700
Data Index: 2363783 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.6191. Min Act: -0.1700
Data Index: 1208275 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.6503. Min Act: -0.1700
Data Index: 7805748 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.6503. Min Act: -0.1700
Data Index: 3416322 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.5566. Min Act: -0.1700
Data Index: 5441482 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.5566. Min Act: -0.1700
Data Index: 4932549 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.4003. Min Act: -0.1700
Data Index: 4333699 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.4003. Min Act: -0.1700
Data Index: 1279749 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.3378. Min Act: -0.1700
Data Index: 3948337 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.3691. Min Act: -0.1700
Data Index: 5296447 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.3066. Min Act: -0.1700
Data Index: 6730819 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.2753. Min Act: -0.1700
Data Index: 7087864 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.2753. Min Act: -0.1700
Data Index: 3881508 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.3066. Min Act: -0.1700
Data Index: 5441475 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.2753. Min Act: -0.1700
Data Index: 6354754 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.2441. Min Act: -0.1700
Data Index: 5081269 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.1816. Min Act: -0.1700
Data Index: 8370288 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9316. Min Range: -6.9316
Max Act: 6.2441. Min Act: -0.1700
Data Index: 8763653 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19