Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6035 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.8945. Min Act: -0.1700
Data Index: 4239281 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.6133. Min Act: -0.1700
Data Index: 8253626 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.5820. Min Act: -0.1700
Data Index: 5660552 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.5820. Min Act: -0.1700
Data Index: 6280648 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.5508. Min Act: -0.1700
Data Index: 2485174 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.5195. Min Act: -0.1700
Data Index: 7591097 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.5195. Min Act: -0.1700
Data Index: 8253621 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.4883. Min Act: -0.1700
Data Index: 1803300 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.4883. Min Act: -0.1700
Data Index: 7631825 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.4570. Min Act: -0.1700
Data Index: 5755501 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.4258. Min Act: -0.1700
Data Index: 7565353 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.4258. Min Act: -0.1700
Data Index: 573509 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.3945. Min Act: -0.1700
Data Index: 8254312 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.3633. Min Act: -0.1700
Data Index: 2900416 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.3945. Min Act: -0.1700
Data Index: 2490818 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.3945. Min Act: -0.1700
Data Index: 1491020 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.3320. Min Act: -0.1700
Data Index: 5796721 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.3945. Min Act: -0.1700
Data Index: 1190061 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.3633. Min Act: -0.1700
Data Index: 2509238 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8945. Min Range: -5.8945
Max Act: 5.3320. Min Act: -0.1700
Data Index: 7531515 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19