Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5963 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.5868. Min Act: -0.1700
Data Index: 5741377 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.1493. Min Act: -0.1700
Data Index: 5970241 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.1180. Min Act: -0.1700
Data Index: 6864259 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.0555. Min Act: -0.1700
Data Index: 556091 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5868. Min Range: -5.5868
Max Act: 5.0243. Min Act: -0.1700
Data Index: 6535609 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.9618. Min Act: -0.1700
Data Index: 8188967 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.9618. Min Act: -0.1700
Data Index: 5038951 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.9618. Min Act: -0.1700
Data Index: 4602995 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.8993. Min Act: -0.1700
Data Index: 4008141 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.8993. Min Act: -0.1700
Data Index: 6415718 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.8055. Min Act: -0.1700
Data Index: 7577233 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.8368. Min Act: -0.1700
Data Index: 8568811 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.8368. Min Act: -0.1700
Data Index: 8174063 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.8055. Min Act: -0.1700
Data Index: 8568812 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.8055. Min Act: -0.1700
Data Index: 5627579 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.8055. Min Act: -0.1700
Data Index: 3941940 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.7430. Min Act: -0.1700
Data Index: 5243779 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.7743. Min Act: -0.1700
Data Index: 2958111 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.7743. Min Act: -0.1700
Data Index: 3585490 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5868. Min Range: -5.5868
Max Act: 4.7430. Min Act: -0.1700
Data Index: 8339897 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19