Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.8088. Min Act: -0.1700
Data Index: 4964030 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.6526. Min Act: -0.1700
Data Index: 7723078 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.6526. Min Act: -0.1700
Data Index: 1254022 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.6213. Min Act: -0.1700
Data Index: 5534285 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.6213. Min Act: -0.1700
Data Index: 8746092 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.5588. Min Act: -0.1700
Data Index: 955262 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.5588. Min Act: -0.1700
Data Index: 4481653 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.5276. Min Act: -0.1700
Data Index: 8204958 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.4338. Min Act: -0.1700
Data Index: 8092474 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.4338. Min Act: -0.1700
Data Index: 4688609 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.4338. Min Act: -0.1700
Data Index: 6830878 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.4026. Min Act: -0.1700
Data Index: 7332488 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.4026. Min Act: -0.1700
Data Index: 4013762 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.4026. Min Act: -0.1700
Data Index: 7335462 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.4026. Min Act: -0.1700
Data Index: 128141 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.4026. Min Act: -0.1700
Data Index: 6475437 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.3713. Min Act: -0.1700
Data Index: 430157 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.3401. Min Act: -0.1700
Data Index: 5166037 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.3713. Min Act: -0.1700
Data Index: 7961892 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8088. Min Range: -7.8088
Max Act: 7.3401. Min Act: -0.1700
Data Index: 7714709 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19