Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4888 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.5127. Min Act: -0.1700
Data Index: 4056633 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.4030. Min Act: -0.1700
Data Index: 5929739 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.3717. Min Act: -0.1700
Data Index: 4224946 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2775. Min Act: -0.1700
Data Index: 2140805 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2618. Min Act: -0.1700
Data Index: 4919028 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2304. Min Act: -0.1700
Data Index: 531671 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2461. Min Act: -0.1700
Data Index: 927218 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2304. Min Act: -0.1700
Data Index: 4854527 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2618. Min Act: -0.1700
Data Index: 8698449 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2461. Min Act: -0.1700
Data Index: 6556231 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2304. Min Act: -0.1700
Data Index: 656273 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2147. Min Act: -0.1700
Data Index: 3621882 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2147. Min Act: -0.1700
Data Index: 2584630 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.1989. Min Act: -0.1700
Data Index: 4954373 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2147. Min Act: -0.1700
Data Index: 2578057 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.1989. Min Act: -0.1700
Data Index: 5006273 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.1832. Min Act: -0.1700
Data Index: 6797595 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2147. Min Act: -0.1700
Data Index: 7544284 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2147. Min Act: -0.1700
Data Index: 7875197 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5127. Min Range: -3.5127
Max Act: 3.2147. Min Act: -0.1700
Data Index: 883930 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19