Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2529. Min Range: -5.2529
Max Act: 5.2529. Min Act: -0.1700
Data Index: 3900173 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.9717. Min Act: -0.1700
Data Index: 2117085 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.9717. Min Act: -0.1700
Data Index: 837724 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.9092. Min Act: -0.1700
Data Index: 7783191 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8779. Min Act: -0.1700
Data Index: 5540014 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8779. Min Act: -0.1700
Data Index: 4603283 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8779. Min Act: -0.1700
Data Index: 6835968 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8779. Min Act: -0.1700
Data Index: 4791497 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 452069 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 8695427 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 6835977 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 2845360 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 4849723 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 2845357 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 4925256 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 7474737 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8154. Min Act: -0.1700
Data Index: 6377225 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8467. Min Act: -0.1700
Data Index: 2760391 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8154. Min Act: -0.1700
Data Index: 5211792 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2529. Min Range: -5.2529
Max Act: 4.8154. Min Act: -0.1700
Data Index: 858503 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19