Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5026 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.5080. Min Act: -0.1700
Data Index: 5445033 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.0080. Min Act: -0.1700
Data Index: 5531684 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9455. Min Act: -0.1700
Data Index: 701527 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.7268. Min Act: -0.1700
Data Index: 5883882 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.6643. Min Act: -0.1700
Data Index: 8423750 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.6330. Min Act: -0.1700
Data Index: 542745 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.6330. Min Act: -0.1700
Data Index: 6019561 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.5705. Min Act: -0.1700
Data Index: 2163099 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.5393. Min Act: -0.1700
Data Index: 5444785 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.4768. Min Act: -0.1700
Data Index: 8373150 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.4455. Min Act: -0.1700
Data Index: 6153655 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.4768. Min Act: -0.1700
Data Index: 2809071 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.4143. Min Act: -0.1700
Data Index: 4562774 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.3830. Min Act: -0.1700
Data Index: 1872265 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.3830. Min Act: -0.1700
Data Index: 4877362 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.3205. Min Act: -0.1700
Data Index: 3393495 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.3205. Min Act: -0.1700
Data Index: 5455694 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.2893. Min Act: -0.1700
Data Index: 1138422 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.2893. Min Act: -0.1700
Data Index: 8035568 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.2580. Min Act: -0.1700
Data Index: 6477639 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19