Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.9141. Min Act: -0.1700
Data Index: 426556 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.7266. Min Act: -0.1700
Data Index: 838012 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.5703. Min Act: -0.1700
Data Index: 294746 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.5703. Min Act: -0.1700
Data Index: 7529875 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.5078. Min Act: -0.1700
Data Index: 3466285 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.4766. Min Act: -0.1700
Data Index: 7320606 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.4141. Min Act: -0.1700
Data Index: 4368692 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.3828. Min Act: -0.1700
Data Index: 887154 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.3828. Min Act: -0.1700
Data Index: 4001444 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.3516. Min Act: -0.1700
Data Index: 4041006 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.3203. Min Act: -0.1700
Data Index: 5845669 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.3203. Min Act: -0.1700
Data Index: 7415551 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.3203. Min Act: -0.1700
Data Index: 6939946 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.2578. Min Act: -0.1700
Data Index: 4934727 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.2891. Min Act: -0.1700
Data Index: 5987689 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.2266. Min Act: -0.1700
Data Index: 1095494 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.1953. Min Act: -0.1700
Data Index: 3666547 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.1953. Min Act: -0.1700
Data Index: 4307998 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.1953. Min Act: -0.1700
Data Index: 1486575 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9141. Min Range: -6.9141
Max Act: 6.1953. Min Act: -0.1700
Data Index: 5836201 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19