Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4078 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.8795. Min Act: -0.1700
Data Index: 2934681 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.8795. Min Act: -0.1700
Data Index: 718274 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.8483. Min Act: -0.1700
Data Index: 2319109 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.8170. Min Act: -0.1700
Data Index: 2047318 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.7858. Min Act: -0.1700
Data Index: 5346614 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.7233. Min Act: -0.1700
Data Index: 4215987 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.7233. Min Act: -0.1700
Data Index: 4038143 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.6295. Min Act: -0.1700
Data Index: 1208097 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5983. Min Act: -0.1700
Data Index: 2654490 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5983. Min Act: -0.1700
Data Index: 6453763 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5983. Min Act: -0.1700
Data Index: 3706830 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.6295. Min Act: -0.1700
Data Index: 5168277 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5983. Min Act: -0.1700
Data Index: 1348753 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5670. Min Act: -0.1700
Data Index: 103539 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5358. Min Act: -0.1700
Data Index: 6562866 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5045. Min Act: -0.1700
Data Index: 4985259 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5045. Min Act: -0.1700
Data Index: 5336702 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.5045. Min Act: -0.1700
Data Index: 8395184 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.4733. Min Act: -0.1700
Data Index: 1010784 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.4733. Min Act: -0.1700
Data Index: 3183937 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19