Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5453 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.6529. Min Act: -0.1700
Data Index: 7145061 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.5279. Min Act: -0.1700
Data Index: 6045414 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.4654. Min Act: -0.1700
Data Index: 3887555 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.3716. Min Act: -0.1700
Data Index: 7055896 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.3091. Min Act: -0.1700
Data Index: 4782638 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.3091. Min Act: -0.1700
Data Index: 2246005 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.2779. Min Act: -0.1700
Data Index: 4832551 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.2466. Min Act: -0.1700
Data Index: 1158396 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.1841. Min Act: -0.1700
Data Index: 6052534 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.1529. Min Act: -0.1700
Data Index: 2776613 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.1529. Min Act: -0.1700
Data Index: 6147406 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.1216. Min Act: -0.1700
Data Index: 3028261 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.1216. Min Act: -0.1700
Data Index: 5319007 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.0904. Min Act: -0.1700
Data Index: 154023 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.0904. Min Act: -0.1700
Data Index: 1494502 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.0904. Min Act: -0.1700
Data Index: 3013816 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.0904. Min Act: -0.1700
Data Index: 649646 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.0591. Min Act: -0.1700
Data Index: 4138541 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.0591. Min Act: -0.1700
Data Index: 5123408 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6529. Min Range: -7.6529
Max Act: 7.0591. Min Act: -0.1700
Data Index: 7943648 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19