Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3153. Min Range: -6.3153
Max Act: 6.3153. Min Act: -0.1700
Data Index: 3064241 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.9090. Min Act: -0.1700
Data Index: 5638309 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.9403. Min Act: -0.1700
Data Index: 8404988 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.8465. Min Act: -0.1700
Data Index: 3361752 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.8153. Min Act: -0.1700
Data Index: 6340909 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.7528. Min Act: -0.1700
Data Index: 7402563 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.7528. Min Act: -0.1700
Data Index: 8194352 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.7528. Min Act: -0.1700
Data Index: 5795258 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.7528. Min Act: -0.1700
Data Index: 656440 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.7528. Min Act: -0.1700
Data Index: 6906230 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.7528. Min Act: -0.1700
Data Index: 6789587 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.7215. Min Act: -0.1700
Data Index: 3585428 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.6903. Min Act: -0.1700
Data Index: 8321708 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.7528. Min Act: -0.1700
Data Index: 186024 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.6903. Min Act: -0.1700
Data Index: 7967501 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.6903. Min Act: -0.1700
Data Index: 1775247 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.6590. Min Act: -0.1700
Data Index: 2709199 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.5653. Min Act: -0.1700
Data Index: 7404132 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.5965. Min Act: -0.1700
Data Index: 3533025 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3153. Min Range: -6.3153
Max Act: 5.5965. Min Act: -0.1700
Data Index: 6424515 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19