Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5160 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.5161. Min Act: -0.1700
Data Index: 6368773 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.2349. Min Act: -0.1700
Data Index: 5248467 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.2661. Min Act: -0.1700
Data Index: 3172181 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.2349. Min Act: -0.1700
Data Index: 2109802 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.0786. Min Act: -0.1700
Data Index: 3835893 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.0786. Min Act: -0.1700
Data Index: 242343 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.0161. Min Act: -0.1700
Data Index: 7190255 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.0161. Min Act: -0.1700
Data Index: 7979536 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.0161. Min Act: -0.1700
Data Index: 2653899 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.0161. Min Act: -0.1700
Data Index: 5752821 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5161. Min Range: -6.5161
Max Act: 6.0161. Min Act: -0.1700
Data Index: 1273665 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.9849. Min Act: -0.1700
Data Index: 7634620 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.9849. Min Act: -0.1700
Data Index: 8222439 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.9536. Min Act: -0.1700
Data Index: 8826393 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.9536. Min Act: -0.1700
Data Index: 4936651 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.9224. Min Act: -0.1700
Data Index: 3091373 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.9224. Min Act: -0.1700
Data Index: 2314185 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.9536. Min Act: -0.1700
Data Index: 6336045 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.8911. Min Act: -0.1700
Data Index: 5048805 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5161. Min Range: -6.5161
Max Act: 5.8911. Min Act: -0.1700
Data Index: 2160202 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19