Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6103 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.8189. Min Act: -0.1700
Data Index: 5239599 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.7564. Min Act: -0.1700
Data Index: 1373492 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.6626. Min Act: -0.1700
Data Index: 7220313 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.6314. Min Act: -0.1700
Data Index: 3604924 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.5064. Min Act: -0.1700
Data Index: 7373432 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.5376. Min Act: -0.1700
Data Index: 3685663 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4439. Min Act: -0.1700
Data Index: 7554950 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4751. Min Act: -0.1700
Data Index: 1957288 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4439. Min Act: -0.1700
Data Index: 4491640 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4439. Min Act: -0.1700
Data Index: 5999324 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.4126. Min Act: -0.1700
Data Index: 5082935 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3814. Min Act: -0.1700
Data Index: 1679283 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3189. Min Act: -0.1700
Data Index: 5082942 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.3189. Min Act: -0.1700
Data Index: 5185333 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.2876. Min Act: -0.1700
Data Index: 1530657 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.2876. Min Act: -0.1700
Data Index: 809841 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.2564. Min Act: -0.1700
Data Index: 7010318 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.2564. Min Act: -0.1700
Data Index: 6285875 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.2251. Min Act: -0.1700
Data Index: 7244686 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8189. Min Range: -6.8189
Max Act: 6.1939. Min Act: -0.1700
Data Index: 3845318 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19