Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4692 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.3900. Min Act: -0.1700
Data Index: 7409591 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.3900. Min Act: -0.1700
Data Index: 428480 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.3275. Min Act: -0.1700
Data Index: 1174823 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.3275. Min Act: -0.1700
Data Index: 770973 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.3275. Min Act: -0.1700
Data Index: 4532299 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.2963. Min Act: -0.1700
Data Index: 644809 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.2963. Min Act: -0.1700
Data Index: 773000 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.3275. Min Act: -0.1700
Data Index: 6082697 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.2337. Min Act: -0.1700
Data Index: 3639252 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.2337. Min Act: -0.1700
Data Index: 7609688 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.2337. Min Act: -0.1700
Data Index: 5374176 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.2025. Min Act: -0.1700
Data Index: 3085883 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.2337. Min Act: -0.1700
Data Index: 3956678 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.2025. Min Act: -0.1700
Data Index: 2341670 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.1712. Min Act: -0.1700
Data Index: 934857 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.1712. Min Act: -0.1700
Data Index: 6214406 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.1712. Min Act: -0.1700
Data Index: 7915078 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.1712. Min Act: -0.1700
Data Index: 5541175 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.1400. Min Act: -0.1700
Data Index: 2732175 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3900. Min Range: -4.3900
Max Act: 4.1400. Min Act: -0.1700
Data Index: 2362551 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19