Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1564 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.3181. Min Act: -0.1700
Data Index: 3615917 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.3181. Min Act: -0.1700
Data Index: 6287722 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.1931. Min Act: -0.1700
Data Index: 388592 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.1306. Min Act: -0.1700
Data Index: 275060 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.1306. Min Act: -0.1700
Data Index: 3673102 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.1306. Min Act: -0.1700
Data Index: 6936269 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.1306. Min Act: -0.1700
Data Index: 4229320 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.0681. Min Act: -0.1700
Data Index: 1521417 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.0681. Min Act: -0.1700
Data Index: 227458 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.0681. Min Act: -0.1700
Data Index: 4451980 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3181. Min Range: -8.3181
Max Act: 8.0056. Min Act: -0.1700
Data Index: 7471355 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.8806. Min Act: -0.1700
Data Index: 6407719 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.9431. Min Act: -0.1700
Data Index: 5740075 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.9431. Min Act: -0.1700
Data Index: 4323744 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.9431. Min Act: -0.1700
Data Index: 2508421 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.9431. Min Act: -0.1700
Data Index: 2706279 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.9431. Min Act: -0.1700
Data Index: 583788 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.9431. Min Act: -0.1700
Data Index: 4469344 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.9431. Min Act: -0.1700
Data Index: 3510325 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3181. Min Range: -8.3181
Max Act: 7.9431. Min Act: -0.1700
Data Index: 371888 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19