Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1873 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.4341. Min Act: -0.1700
Data Index: 7921546 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.4028. Min Act: -0.1700
Data Index: 8699403 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.3716. Min Act: -0.1700
Data Index: 6991280 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.3403. Min Act: -0.1700
Data Index: 264341 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.3403. Min Act: -0.1700
Data Index: 3273261 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.3091. Min Act: -0.1700
Data Index: 451301 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.3091. Min Act: -0.1700
Data Index: 760434 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.2778. Min Act: -0.1700
Data Index: 6847942 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.2778. Min Act: -0.1700
Data Index: 4004743 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.2466. Min Act: -0.1700
Data Index: 4220979 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.2466. Min Act: -0.1700
Data Index: 7147833 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.1528. Min Act: -0.1700
Data Index: 6858304 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.1528. Min Act: -0.1700
Data Index: 6157488 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.1528. Min Act: -0.1700
Data Index: 5643268 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.1216. Min Act: -0.1700
Data Index: 3761524 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.1528. Min Act: -0.1700
Data Index: 321075 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.1216. Min Act: -0.1700
Data Index: 2008965 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.0591. Min Act: -0.1700
Data Index: 7116177 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.0903. Min Act: -0.1700
Data Index: 5889931 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4341. Min Range: -7.4341
Max Act: 7.0903. Min Act: -0.1700
Data Index: 1011677 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19