Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4121 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2143. Min Range: -6.2143
Max Act: 6.2143. Min Act: -0.1700
Data Index: 3345864 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2143. Min Range: -6.2143
Max Act: 6.0580. Min Act: -0.1700
Data Index: 3984641 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.9330. Min Act: -0.1700
Data Index: 4149651 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.9330. Min Act: -0.1700
Data Index: 2051396 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.8705. Min Act: -0.1700
Data Index: 4594133 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.8393. Min Act: -0.1700
Data Index: 645198 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.8393. Min Act: -0.1700
Data Index: 4512208 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.8080. Min Act: -0.1700
Data Index: 2103796 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.8080. Min Act: -0.1700
Data Index: 6679174 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.7455. Min Act: -0.1700
Data Index: 7370954 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.7455. Min Act: -0.1700
Data Index: 6700853 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.7143. Min Act: -0.1700
Data Index: 2096416 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.7143. Min Act: -0.1700
Data Index: 7608540 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.6830. Min Act: -0.1700
Data Index: 7505424 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.6830. Min Act: -0.1700
Data Index: 2120989 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.6518. Min Act: -0.1700
Data Index: 2616024 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.6518. Min Act: -0.1700
Data Index: 7806318 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.6518. Min Act: -0.1700
Data Index: 4025202 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.6518. Min Act: -0.1700
Data Index: 3345863 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2143. Min Range: -6.2143
Max Act: 5.6518. Min Act: -0.1700
Data Index: 7179164 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19