Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5140 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.7085. Min Act: -0.1700
Data Index: 1441785 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.6460. Min Act: -0.1700
Data Index: 1598535 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.4585. Min Act: -0.1700
Data Index: 3158718 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.5210. Min Act: -0.1700
Data Index: 916430 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.3960. Min Act: -0.1700
Data Index: 477394 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.4585. Min Act: -0.1700
Data Index: 2249504 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.4585. Min Act: -0.1700
Data Index: 6532656 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.3960. Min Act: -0.1700
Data Index: 5323081 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.3960. Min Act: -0.1700
Data Index: 3967050 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.3960. Min Act: -0.1700
Data Index: 4904695 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.3960. Min Act: -0.1700
Data Index: 5303581 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.3335. Min Act: -0.1700
Data Index: 6820254 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.2710. Min Act: -0.1700
Data Index: 3202576 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.2085. Min Act: -0.1700
Data Index: 5403472 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.2710. Min Act: -0.1700
Data Index: 272298 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.2710. Min Act: -0.1700
Data Index: 3898289 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.2710. Min Act: -0.1700
Data Index: 2177240 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.2710. Min Act: -0.1700
Data Index: 4972967 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.2710. Min Act: -0.1700
Data Index: 1959677 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7085. Min Range: -8.7085
Max Act: 8.2710. Min Act: -0.1700
Data Index: 2911185 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19