Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0148. Min Range: -7.0148
Max Act: 7.0148. Min Act: -0.1700
Data Index: 3709553 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0148. Min Range: -7.0148
Max Act: 7.0148. Min Act: -0.1700
Data Index: 1334070 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.8273. Min Act: -0.1700
Data Index: 6592494 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.8586. Min Act: -0.1700
Data Index: 4953898 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7961. Min Act: -0.1700
Data Index: 7046771 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7648. Min Act: -0.1700
Data Index: 4742266 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7648. Min Act: -0.1700
Data Index: 4512981 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7648. Min Act: -0.1700
Data Index: 3477641 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7336. Min Act: -0.1700
Data Index: 8510673 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7336. Min Act: -0.1700
Data Index: 6561392 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7336. Min Act: -0.1700
Data Index: 7235472 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7023. Min Act: -0.1700
Data Index: 4264407 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.7023. Min Act: -0.1700
Data Index: 1262522 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.6711. Min Act: -0.1700
Data Index: 316227 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.6711. Min Act: -0.1700
Data Index: 8760249 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.6711. Min Act: -0.1700
Data Index: 949729 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.6711. Min Act: -0.1700
Data Index: 7480202 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.6711. Min Act: -0.1700
Data Index: 6721861 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.6398. Min Act: -0.1700
Data Index: 7423524 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0148. Min Range: -7.0148
Max Act: 6.6086. Min Act: -0.1700
Data Index: 6627622 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19