Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4511 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.6739. Min Act: -0.1700
Data Index: 5494558 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.5489. Min Act: -0.1700
Data Index: 5873531 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.4239. Min Act: -0.1700
Data Index: 4173834 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.4239. Min Act: -0.1700
Data Index: 7060397 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.3614. Min Act: -0.1700
Data Index: 3397687 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.3614. Min Act: -0.1700
Data Index: 7236610 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.3614. Min Act: -0.1700
Data Index: 4624306 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.3302. Min Act: -0.1700
Data Index: 2052670 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.2989. Min Act: -0.1700
Data Index: 8462051 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.2364. Min Act: -0.1700
Data Index: 5347569 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.2364. Min Act: -0.1700
Data Index: 7399072 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.2052. Min Act: -0.1700
Data Index: 3598276 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.2052. Min Act: -0.1700
Data Index: 2095159 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.1739. Min Act: -0.1700
Data Index: 7780568 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.1739. Min Act: -0.1700
Data Index: 3626786 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.1427. Min Act: -0.1700
Data Index: 6547283 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.1427. Min Act: -0.1700
Data Index: 2997695 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.1114. Min Act: -0.1700
Data Index: 262211 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.0802. Min Act: -0.1700
Data Index: 6991650 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6739. Min Range: -7.6739
Max Act: 7.0489. Min Act: -0.1700
Data Index: 3435612 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19