Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.3158. Min Act: -0.1700
Data Index: 2499116 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.2845. Min Act: -0.1700
Data Index: 8435897 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.2220. Min Act: -0.1700
Data Index: 7990084 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.1595. Min Act: -0.1700
Data Index: 998256 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.1595. Min Act: -0.1700
Data Index: 1287611 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.1595. Min Act: -0.1700
Data Index: 6693340 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.1283. Min Act: -0.1700
Data Index: 1404544 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.1283. Min Act: -0.1700
Data Index: 6505518 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0970. Min Act: -0.1699
Data Index: 8515243 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0970. Min Act: -0.1700
Data Index: 6200868 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0658. Min Act: -0.1700
Data Index: 1018088 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0658. Min Act: -0.1700
Data Index: 4394938 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0658. Min Act: -0.1700
Data Index: 492315 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0658. Min Act: -0.1700
Data Index: 4526342 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0658. Min Act: -0.1700
Data Index: 7556257 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0658. Min Act: -0.1700
Data Index: 5446488 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0970. Min Act: -0.1700
Data Index: 1745186 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0970. Min Act: -0.1700
Data Index: 2219357 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0658. Min Act: -0.1700
Data Index: 5737166 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3158. Min Range: -5.3158
Max Act: 5.0658. Min Act: -0.1700
Data Index: 751086 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19