Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4101 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.7705. Min Act: -0.1700
Data Index: 7110211 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.7393. Min Act: -0.1700
Data Index: 3981340 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.6455. Min Act: -0.1700
Data Index: 3496093 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.6143. Min Act: -0.1700
Data Index: 2028155 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.5518. Min Act: -0.1700
Data Index: 7055412 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.5205. Min Act: -0.1700
Data Index: 7950793 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.4580. Min Act: -0.1700
Data Index: 1133370 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.4580. Min Act: -0.1700
Data Index: 3150020 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.4268. Min Act: -0.1700
Data Index: 7615433 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.4268. Min Act: -0.1700
Data Index: 1211554 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.3955. Min Act: -0.1700
Data Index: 8268825 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.3643. Min Act: -0.1700
Data Index: 657134 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.3018. Min Act: -0.1700
Data Index: 1288247 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.3018. Min Act: -0.1700
Data Index: 3522203 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.3018. Min Act: -0.1700
Data Index: 1790077 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.2705. Min Act: -0.1700
Data Index: 6621380 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.2393. Min Act: -0.1700
Data Index: 5134515 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.2393. Min Act: -0.1700
Data Index: 2410943 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.2393. Min Act: -0.1700
Data Index: 346391 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7705. Min Range: -5.7705
Max Act: 5.2393. Min Act: -0.1700
Data Index: 2322072 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19