Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4756 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.5837. Min Act: -0.1700
Data Index: 6848306 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.5212. Min Act: -0.1700
Data Index: 385412 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.5212. Min Act: -0.1700
Data Index: 8759145 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.4900. Min Act: -0.1700
Data Index: 8651667 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.4275. Min Act: -0.1700
Data Index: 2103238 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.4275. Min Act: -0.1700
Data Index: 1078411 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.3337. Min Act: -0.1700
Data Index: 7522154 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.3025. Min Act: -0.1700
Data Index: 7054734 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.3025. Min Act: -0.1700
Data Index: 5083533 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2712. Min Act: -0.1700
Data Index: 2323909 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2712. Min Act: -0.1700
Data Index: 2961121 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2400. Min Act: -0.1700
Data Index: 8548058 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2400. Min Act: -0.1700
Data Index: 1952365 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2712. Min Act: -0.1700
Data Index: 7114265 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2087. Min Act: -0.1700
Data Index: 3212718 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2400. Min Act: -0.1700
Data Index: 3703012 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2400. Min Act: -0.1700
Data Index: 3910681 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2087. Min Act: -0.1700
Data Index: 1091760 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2087. Min Act: -0.1700
Data Index: 7114167 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5837. Min Range: -5.5837
Max Act: 5.2087. Min Act: -0.1700
Data Index: 4833296 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19