Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.4866. Min Act: -0.1700
Data Index: 7376900 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.4866. Min Act: -0.1700
Data Index: 7893982 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.3929. Min Act: -0.1700
Data Index: 36557 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.3929. Min Act: -0.1700
Data Index: 4356946 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.3616. Min Act: -0.1700
Data Index: 294441 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.3304. Min Act: -0.1700
Data Index: 6611522 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.3304. Min Act: -0.1700
Data Index: 393453 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.3304. Min Act: -0.1700
Data Index: 6611523 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2991. Min Act: -0.1700
Data Index: 2544696 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2991. Min Act: -0.1700
Data Index: 4999862 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.3304. Min Act: -0.1700
Data Index: 7376896 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2679. Min Act: -0.1700
Data Index: 3465090 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2679. Min Act: -0.1700
Data Index: 281231 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2679. Min Act: -0.1700
Data Index: 7622656 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2679. Min Act: -0.1700
Data Index: 3123092 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2366. Min Act: -0.1700
Data Index: 6889896 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2054. Min Act: -0.1700
Data Index: 4242993 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2054. Min Act: -0.1700
Data Index: 633561 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2054. Min Act: -0.1700
Data Index: 6610953 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4866. Min Range: -6.4866
Max Act: 6.2054. Min Act: -0.1700
Data Index: 4627981 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19