Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0786. Min Range: -6.0786
Max Act: 6.0786. Min Act: -0.1700
Data Index: 3596844 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.9223. Min Act: -0.1700
Data Index: 6532142 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.8911. Min Act: -0.1700
Data Index: 3949231 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.8598. Min Act: -0.1700
Data Index: 1041674 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.8286. Min Act: -0.1700
Data Index: 1766716 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.7973. Min Act: -0.1700
Data Index: 449310 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.7036. Min Act: -0.1700
Data Index: 2857912 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.7348. Min Act: -0.1700
Data Index: 2174134 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.7036. Min Act: -0.1700
Data Index: 514829 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.6411. Min Act: -0.1700
Data Index: 2662493 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.6411. Min Act: -0.1700
Data Index: 309161 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.6098. Min Act: -0.1700
Data Index: 6580745 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.6098. Min Act: -0.1700
Data Index: 7564179 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.5786. Min Act: -0.1700
Data Index: 937327 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.5161. Min Act: -0.1700
Data Index: 2298288 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.5161. Min Act: -0.1700
Data Index: 8617780 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.5161. Min Act: -0.1700
Data Index: 228233 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.5161. Min Act: -0.1700
Data Index: 6309674 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.4848. Min Act: -0.1700
Data Index: 2848085 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0786. Min Range: -6.0786
Max Act: 5.4848. Min Act: -0.1700
Data Index: 262081 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19