Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4519 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.6443. Min Act: -0.1700
Data Index: 5741905 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.5745. Min Act: -0.1700
Data Index: 1871041 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.5570. Min Act: -0.1700
Data Index: 4154247 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4693. Min Act: -0.1700
Data Index: 4589321 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4693. Min Act: -0.1700
Data Index: 1765675 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4517. Min Act: -0.1700
Data Index: 2515568 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4693. Min Act: -0.1700
Data Index: 405194 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4517. Min Act: -0.1700
Data Index: 5405772 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4517. Min Act: -0.1700
Data Index: 6400954 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4517. Min Act: -0.1700
Data Index: 6157389 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4517. Min Act: -0.1700
Data Index: 4998706 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4341. Min Act: -0.1700
Data Index: 5993075 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4341. Min Act: -0.1700
Data Index: 8081964 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4341. Min Act: -0.1700
Data Index: 467147 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4341. Min Act: -0.1700
Data Index: 8648395 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4165. Min Act: -0.1700
Data Index: 443072 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.3989. Min Act: -0.1700
Data Index: 1232355 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4165. Min Act: -0.1700
Data Index: 2398683 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4165. Min Act: -0.1700
Data Index: 2246603 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6443. Min Range: -1.6443
Max Act: 1.4165. Min Act: -0.1700
Data Index: 5261799 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19