Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.9578. Min Act: -0.1700
Data Index: 497897 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.8953. Min Act: -0.1700
Data Index: 26391 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.9266. Min Act: -0.1700
Data Index: 5190552 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.8953. Min Act: -0.1700
Data Index: 8645368 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.8953. Min Act: -0.1700
Data Index: 3464963 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.8953. Min Act: -0.1700
Data Index: 8720539 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.8641. Min Act: -0.1700
Data Index: 8162676 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.8328. Min Act: -0.1700
Data Index: 7266272 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.8016. Min Act: -0.1700
Data Index: 6129194 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.8016. Min Act: -0.1700
Data Index: 2154949 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.7703. Min Act: -0.1700
Data Index: 4577506 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.7391. Min Act: -0.1700
Data Index: 8391870 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.6766. Min Act: -0.1700
Data Index: 7986542 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.7078. Min Act: -0.1700
Data Index: 2125208 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.7078. Min Act: -0.1700
Data Index: 3312204 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.7078. Min Act: -0.1700
Data Index: 4741289 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.6766. Min Act: -0.1700
Data Index: 5156245 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.6766. Min Act: -0.1700
Data Index: 4845818 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.6453. Min Act: -0.1700
Data Index: 2550240 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9578. Min Range: -5.9578
Max Act: 5.6453. Min Act: -0.1700
Data Index: 4807088 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19