Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.4265. Min Act: -0.1700
Data Index: 689432 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.3015. Min Act: -0.1700
Data Index: 4550091 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.2077. Min Act: -0.1700
Data Index: 5028590 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.1452. Min Act: -0.1700
Data Index: 6067872 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.1140. Min Act: -0.1700
Data Index: 6374059 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0827. Min Act: -0.1700
Data Index: 2826214 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0827. Min Act: -0.1700
Data Index: 7749386 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0827. Min Act: -0.1700
Data Index: 2128171 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0515. Min Act: -0.1700
Data Index: 3854591 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0202. Min Act: -0.1700
Data Index: 5771626 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0515. Min Act: -0.1700
Data Index: 6043182 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0202. Min Act: -0.1700
Data Index: 8185694 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0515. Min Act: -0.1700
Data Index: 2495827 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0515. Min Act: -0.1700
Data Index: 1518331 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0202. Min Act: -0.1700
Data Index: 1353825 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4265. Min Range: -5.4265
Max Act: 5.0202. Min Act: -0.1700
Data Index: 5442673 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4265. Min Range: -5.4265
Max Act: 4.9577. Min Act: -0.1700
Data Index: 3683206 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4265. Min Range: -5.4265
Max Act: 4.9890. Min Act: -0.1700
Data Index: 6013270 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4265. Min Range: -5.4265
Max Act: 4.9890. Min Act: -0.1700
Data Index: 850916 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4265. Min Range: -5.4265
Max Act: 4.9890. Min Act: -0.1700
Data Index: 6043186 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19