Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.7549. Min Act: -0.1700
Data Index: 3858571 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.3799. Min Act: -0.1700
Data Index: 7233837 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.3174. Min Act: -0.1700
Data Index: 4235676 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.3174. Min Act: -0.1700
Data Index: 2991174 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.3174. Min Act: -0.1700
Data Index: 5619992 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.2549. Min Act: -0.1700
Data Index: 240179 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.2237. Min Act: -0.1700
Data Index: 106110 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.1924. Min Act: -0.1700
Data Index: 7343739 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0674. Min Act: -0.1700
Data Index: 2376799 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.1299. Min Act: -0.1700
Data Index: 6306022 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0987. Min Act: -0.1700
Data Index: 6508271 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0674. Min Act: -0.1700
Data Index: 8227092 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0987. Min Act: -0.1700
Data Index: 6190827 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0362. Min Act: -0.1700
Data Index: 7321520 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0362. Min Act: -0.1700
Data Index: 1781948 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0362. Min Act: -0.1700
Data Index: 5760842 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7549. Min Range: -7.7549
Max Act: 6.9737. Min Act: -0.1700
Data Index: 5596453 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0049. Min Act: -0.1700
Data Index: 2113943 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7549. Min Range: -7.7549
Max Act: 7.0049. Min Act: -0.1700
Data Index: 3939805 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7549. Min Range: -7.7549
Max Act: 6.9424. Min Act: -0.1700
Data Index: 6239373 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19