Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5804 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.7165. Min Act: -0.1700
Data Index: 7511012 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.6226. Min Act: -0.1700
Data Index: 4993498 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.6069. Min Act: -0.1700
Data Index: 831665 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.5600. Min Act: -0.1700
Data Index: 3466237 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.5287. Min Act: -0.1700
Data Index: 5022988 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.5443. Min Act: -0.1700
Data Index: 4477579 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.5287. Min Act: -0.1700
Data Index: 6626237 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.5130. Min Act: -0.1700
Data Index: 8191627 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.5130. Min Act: -0.1700
Data Index: 2336226 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.5130. Min Act: -0.1700
Data Index: 4137897 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4817. Min Act: -0.1700
Data Index: 6951761 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4973. Min Act: -0.1700
Data Index: 995509 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4817. Min Act: -0.1700
Data Index: 5331431 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4817. Min Act: -0.1700
Data Index: 6644063 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4660. Min Act: -0.1700
Data Index: 7402755 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4503. Min Act: -0.1700
Data Index: 8594658 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4347. Min Act: -0.1700
Data Index: 7487786 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4503. Min Act: -0.1700
Data Index: 2219699 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4503. Min Act: -0.1700
Data Index: 5115085 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7165. Min Range: -3.7165
Max Act: 3.4503. Min Act: -0.1700
Data Index: 7013373 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19