Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.4551. Min Act: -0.1700
Data Index: 8725709 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.3926. Min Act: -0.1700
Data Index: 3266534 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.3926. Min Act: -0.1700
Data Index: 2325743 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.2989. Min Act: -0.1700
Data Index: 6758521 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.2051. Min Act: -0.1700
Data Index: 7832550 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.2051. Min Act: -0.1700
Data Index: 2217955 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.2051. Min Act: -0.1700
Data Index: 6799329 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1426. Min Act: -0.1700
Data Index: 7637018 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1114. Min Act: -0.1700
Data Index: 274510 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1114. Min Act: -0.1700
Data Index: 5188423 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.1114. Min Act: -0.1700
Data Index: 911856 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0801. Min Act: -0.1700
Data Index: 7210168 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0801. Min Act: -0.1700
Data Index: 6959140 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0801. Min Act: -0.1700
Data Index: 6111445 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0801. Min Act: -0.1700
Data Index: 6758519 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0801. Min Act: -0.1700
Data Index: 3389787 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0489. Min Act: -0.1700
Data Index: 7499421 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0176. Min Act: -0.1700
Data Index: 3980271 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0176. Min Act: -0.1700
Data Index: 6297627 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4551. Min Range: -5.4551
Max Act: 5.0176. Min Act: -0.1700
Data Index: 4215239 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19