Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5083 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.5179. Min Act: -0.1700
Data Index: 3899356 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.3925. Min Act: -0.1700
Data Index: 3505552 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.3298. Min Act: -0.1700
Data Index: 1299656 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.2984. Min Act: -0.1700
Data Index: 6465773 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.2827. Min Act: -0.1700
Data Index: 4069011 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.2513. Min Act: -0.1700
Data Index: 5402805 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.2356. Min Act: -0.1700
Data Index: 286895 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.2356. Min Act: -0.1700
Data Index: 2299961 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.2356. Min Act: -0.1700
Data Index: 987760 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.2356. Min Act: -0.1700
Data Index: 289212 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.2199. Min Act: -0.1700
Data Index: 4028900 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1727. Min Act: -0.1700
Data Index: 3696344 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1727. Min Act: -0.1700
Data Index: 905622 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1884. Min Act: -0.1700
Data Index: 757132 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1727. Min Act: -0.1700
Data Index: 6374902 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1727. Min Act: -0.1700
Data Index: 6748773 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1569. Min Act: -0.1700
Data Index: 4007150 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1569. Min Act: -0.1700
Data Index: 253979 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1569. Min Act: -0.1700
Data Index: 369674 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5179. Min Range: -3.5179
Max Act: 3.1412. Min Act: -0.1700
Data Index: 625997 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19