Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5873 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.5351. Min Act: -0.1700
Data Index: 3084052 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.5194. Min Act: -0.1700
Data Index: 7781122 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.5038. Min Act: -0.1700
Data Index: 7781124 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.5038. Min Act: -0.1700
Data Index: 8338365 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.5194. Min Act: -0.1700
Data Index: 1170264 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4881. Min Act: -0.1700
Data Index: 2868333 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4881. Min Act: -0.1700
Data Index: 2868336 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4568. Min Act: -0.1700
Data Index: 2904660 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4568. Min Act: -0.1700
Data Index: 3216060 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4568. Min Act: -0.1700
Data Index: 2356022 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4411. Min Act: -0.1700
Data Index: 5278049 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4568. Min Act: -0.1700
Data Index: 2259916 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4254. Min Act: -0.1700
Data Index: 354120 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4254. Min Act: -0.1700
Data Index: 2850797 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4097. Min Act: -0.1700
Data Index: 7369048 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.3941. Min Act: -0.1700
Data Index: 2290783 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4097. Min Act: -0.1700
Data Index: 3099256 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.4097. Min Act: -0.1700
Data Index: 8394482 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.3941. Min Act: -0.1700
Data Index: 7023993 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5351. Min Range: -3.5351
Max Act: 3.3941. Min Act: -0.1700
Data Index: 3519958 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19