Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1646 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.5663. Min Act: -0.1700
Data Index: 4456140 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.3475. Min Act: -0.1700
Data Index: 5492747 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.3163. Min Act: -0.1700
Data Index: 196070 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.2225. Min Act: -0.1700
Data Index: 1096839 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.1600. Min Act: -0.1700
Data Index: 2380206 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.1600. Min Act: -0.1700
Data Index: 3125326 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.1288. Min Act: -0.1700
Data Index: 3952227 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.1288. Min Act: -0.1700
Data Index: 7200913 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.1288. Min Act: -0.1700
Data Index: 640234 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0975. Min Act: -0.1700
Data Index: 7095750 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0975. Min Act: -0.1700
Data Index: 5875565 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0975. Min Act: -0.1700
Data Index: 8426378 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0975. Min Act: -0.1700
Data Index: 3787513 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0663. Min Act: -0.1700
Data Index: 8806629 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0663. Min Act: -0.1700
Data Index: 2616795 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0663. Min Act: -0.1700
Data Index: 442836 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0663. Min Act: -0.1700
Data Index: 3195049 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0663. Min Act: -0.1700
Data Index: 5426158 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0350. Min Act: -0.1700
Data Index: 546938 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5663. Min Range: -4.5663
Max Act: 4.0350. Min Act: -0.1700
Data Index: 6767092 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19