Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5225. Min Range: -5.5225
Max Act: 5.5225. Min Act: -0.1700
Data Index: 304136 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5225. Min Range: -5.5225
Max Act: 5.1475. Min Act: -0.1700
Data Index: 4400567 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5225. Min Range: -5.5225
Max Act: 5.0850. Min Act: -0.1700
Data Index: 8831898 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.9913. Min Act: -0.1700
Data Index: 789856 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.9913. Min Act: -0.1700
Data Index: 8813282 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.9913. Min Act: -0.1700
Data Index: 1479099 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.9288. Min Act: -0.1700
Data Index: 4603233 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8975. Min Act: -0.1700
Data Index: 1869455 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8975. Min Act: -0.1700
Data Index: 3287010 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8663. Min Act: -0.1700
Data Index: 1196036 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8350. Min Act: -0.1700
Data Index: 3032670 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8663. Min Act: -0.1700
Data Index: 8608466 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8663. Min Act: -0.1700
Data Index: 1658868 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8350. Min Act: -0.1700
Data Index: 6838507 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8350. Min Act: -0.1700
Data Index: 5092586 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8350. Min Act: -0.1700
Data Index: 7385124 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8038. Min Act: -0.1700
Data Index: 4789851 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8038. Min Act: -0.1700
Data Index: 2909222 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.8038. Min Act: -0.1700
Data Index: 869255 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5225. Min Range: -5.5225
Max Act: 4.7725. Min Act: -0.1700
Data Index: 3270312 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19