Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0658. Min Range: -3.0658
Max Act: 3.0658. Min Act: -0.1700
Data Index: 3019905 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0658. Min Range: -3.0658
Max Act: 3.0658. Min Act: -0.1700
Data Index: 3667377 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0658. Min Range: -3.0658
Max Act: 3.0185. Min Act: -0.1700
Data Index: 3696290 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0658. Min Range: -3.0658
Max Act: 3.0185. Min Act: -0.1700
Data Index: 1852258 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0658. Min Range: -3.0658
Max Act: 3.0027. Min Act: -0.1700
Data Index: 7691577 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9868. Min Act: -0.1700
Data Index: 1579926 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9710. Min Act: -0.1700
Data Index: 3764068 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9710. Min Act: -0.1700
Data Index: 2770822 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9552. Min Act: -0.1700
Data Index: 6134616 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9235. Min Act: -0.1700
Data Index: 4979111 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9235. Min Act: -0.1700
Data Index: 2446426 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9235. Min Act: -0.1700
Data Index: 5897450 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9077. Min Act: -0.1700
Data Index: 4490256 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9077. Min Act: -0.1700
Data Index: 2302648 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9077. Min Act: -0.1700
Data Index: 2720537 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9077. Min Act: -0.1700
Data Index: 8129693 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8918. Min Act: -0.1700
Data Index: 5303401 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8760. Min Act: -0.1700
Data Index: 1901831 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8918. Min Act: -0.1700
Data Index: 3153563 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8918. Min Act: -0.1700
Data Index: 7782317 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19