Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4064. Min Range: -6.4064
Max Act: 6.4064. Min Act: -0.1700
Data Index: 1142840 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4064. Min Range: -6.4064
Max Act: 6.3127. Min Act: -0.1700
Data Index: 7009033 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4064. Min Range: -6.4064
Max Act: 6.2814. Min Act: -0.1700
Data Index: 3292364 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4064. Min Range: -6.4064
Max Act: 6.1252. Min Act: -0.1700
Data Index: 4907501 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4064. Min Range: -6.4064
Max Act: 6.1252. Min Act: -0.1700
Data Index: 7809561 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4064. Min Range: -6.4064
Max Act: 6.0627. Min Act: -0.1700
Data Index: 6000326 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4064. Min Range: -6.4064
Max Act: 6.0627. Min Act: -0.1700
Data Index: 5027873 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4064. Min Range: -6.4064
Max Act: 6.0002. Min Act: -0.1700
Data Index: 4716785 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.9689. Min Act: -0.1700
Data Index: 7346251 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.9377. Min Act: -0.1700
Data Index: 3570407 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.8752. Min Act: -0.1700
Data Index: 3676918 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.8127. Min Act: -0.1700
Data Index: 6281776 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.8439. Min Act: -0.1700
Data Index: 7490942 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.8127. Min Act: -0.1700
Data Index: 4851387 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.8127. Min Act: -0.1700
Data Index: 7536249 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.7814. Min Act: -0.1700
Data Index: 7300467 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.7814. Min Act: -0.1700
Data Index: 5571479 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.7814. Min Act: -0.1700
Data Index: 5403546 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.7502. Min Act: -0.1700
Data Index: 225258 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4064. Min Range: -6.4064
Max Act: 5.7502. Min Act: -0.1700
Data Index: 3407091 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19