Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3506. Min Range: -6.3506
Max Act: 6.3506. Min Act: -0.1700
Data Index: 4012856 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3506. Min Range: -6.3506
Max Act: 6.1631. Min Act: -0.1700
Data Index: 1593464 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.9443. Min Act: -0.1700
Data Index: 1575612 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.9131. Min Act: -0.1700
Data Index: 3137066 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.8818. Min Act: -0.1700
Data Index: 177211 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.8506. Min Act: -0.1700
Data Index: 47957 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.8506. Min Act: -0.1700
Data Index: 4198318 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.8506. Min Act: -0.1700
Data Index: 392372 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.8506. Min Act: -0.1700
Data Index: 8201628 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.8506. Min Act: -0.1700
Data Index: 6856062 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.8506. Min Act: -0.1700
Data Index: 5798681 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.8193. Min Act: -0.1700
Data Index: 3002650 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.7256. Min Act: -0.1700
Data Index: 4322080 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.7256. Min Act: -0.1700
Data Index: 374998 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.7256. Min Act: -0.1700
Data Index: 5329130 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.7256. Min Act: -0.1700
Data Index: 8605422 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.7256. Min Act: -0.1700
Data Index: 2932701 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.6943. Min Act: -0.1700
Data Index: 3151377 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.6943. Min Act: -0.1700
Data Index: 5680402 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3506. Min Range: -6.3506
Max Act: 5.6943. Min Act: -0.1700
Data Index: 7810765 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19