Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.4408. Min Act: -0.1700
Data Index: 6014096 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.4095. Min Act: -0.1700
Data Index: 5314413 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.3783. Min Act: -0.1700
Data Index: 1679630 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.3470. Min Act: -0.1700
Data Index: 7999325 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.3158. Min Act: -0.1700
Data Index: 638460 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.3158. Min Act: -0.1700
Data Index: 5531340 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.3158. Min Act: -0.1700
Data Index: 1433951 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.3158. Min Act: -0.1700
Data Index: 4558500 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.2845. Min Act: -0.1700
Data Index: 4697397 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.2845. Min Act: -0.1700
Data Index: 6617761 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.2533. Min Act: -0.1700
Data Index: 4697398 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.2533. Min Act: -0.1700
Data Index: 370802 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.2533. Min Act: -0.1700
Data Index: 5323661 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.2220. Min Act: -0.1700
Data Index: 699234 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.2220. Min Act: -0.1700
Data Index: 5835650 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.2220. Min Act: -0.1700
Data Index: 8362453 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.1908. Min Act: -0.1700
Data Index: 7942664 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.1908. Min Act: -0.1700
Data Index: 5911206 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.1908. Min Act: -0.1700
Data Index: 5084461 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4408. Min Range: -4.4408
Max Act: 4.1908. Min Act: -0.1700
Data Index: 3411150 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19