Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.5883. Min Act: -0.1700
Data Index: 5026495 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.4008. Min Act: -0.1700
Data Index: 6037043 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.4633. Min Act: -0.1700
Data Index: 2191183 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.4008. Min Act: -0.1700
Data Index: 8633306 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.4008. Min Act: -0.1700
Data Index: 7297271 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.3383. Min Act: -0.1700
Data Index: 2425411 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.3383. Min Act: -0.1700
Data Index: 7635489 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.3383. Min Act: -0.1700
Data Index: 8053328 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.2758. Min Act: -0.1700
Data Index: 2186306 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.2758. Min Act: -0.1700
Data Index: 190856 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.2758. Min Act: -0.1700
Data Index: 1575054 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.1820. Min Act: -0.1700
Data Index: 7476366 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.0883. Min Act: -0.1700
Data Index: 7209580 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.1195. Min Act: -0.1700
Data Index: 1792626 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.0258. Min Act: -0.1700
Data Index: 8633305 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.0258. Min Act: -0.1700
Data Index: 1563971 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.0258. Min Act: -0.1700
Data Index: 4113318 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5883. Min Range: -8.5883
Max Act: 8.0570. Min Act: -0.1700
Data Index: 5733316 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5883. Min Range: -8.5883
Max Act: 7.9633. Min Act: -0.1700
Data Index: 2825304 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5883. Min Range: -8.5883
Max Act: 7.9945. Min Act: -0.1700
Data Index: 4671214 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19