Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0203. Min Range: -7.0203
Max Act: 7.0203. Min Act: -0.1700
Data Index: 1396958 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.7078. Min Act: -0.1700
Data Index: 6535798 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.6766. Min Act: -0.1700
Data Index: 4972955 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.5828. Min Act: -0.1700
Data Index: 5302291 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.5516. Min Act: -0.1700
Data Index: 2770144 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.5203. Min Act: -0.1700
Data Index: 2347257 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.4578. Min Act: -0.1700
Data Index: 4716031 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3641. Min Act: -0.1700
Data Index: 5432138 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3641. Min Act: -0.1700
Data Index: 3000267 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3328. Min Act: -0.1700
Data Index: 6960738 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3016. Min Act: -0.1700
Data Index: 4475982 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3016. Min Act: -0.1700
Data Index: 3297738 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3016. Min Act: -0.1700
Data Index: 4979415 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3016. Min Act: -0.1700
Data Index: 8639341 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3016. Min Act: -0.1700
Data Index: 4343545 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.3016. Min Act: -0.1700
Data Index: 6467372 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.2703. Min Act: -0.1700
Data Index: 2861418 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.2703. Min Act: -0.1700
Data Index: 1942422 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.2391. Min Act: -0.1700
Data Index: 3378725 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0203. Min Range: -7.0203
Max Act: 6.2391. Min Act: -0.1700
Data Index: 5396963 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19