Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4726 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.9840. Min Act: -0.1700
Data Index: 2758647 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.9215. Min Act: -0.1700
Data Index: 369743 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.9215. Min Act: -0.1700
Data Index: 7515714 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7965. Min Act: -0.1700
Data Index: 4550500 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.8590. Min Act: -0.1700
Data Index: 7903303 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.8590. Min Act: -0.1700
Data Index: 5896326 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.8590. Min Act: -0.1700
Data Index: 2382157 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7965. Min Act: -0.1700
Data Index: 7753418 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7965. Min Act: -0.1700
Data Index: 3039867 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7965. Min Act: -0.1700
Data Index: 8746612 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7340. Min Act: -0.1700
Data Index: 2938314 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7340. Min Act: -0.1700
Data Index: 1876189 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7340. Min Act: -0.1700
Data Index: 6763446 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7340. Min Act: -0.1700
Data Index: 525339 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.7340. Min Act: -0.1700
Data Index: 3275331 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.6715. Min Act: -0.1700
Data Index: 3370135 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.6715. Min Act: -0.1700
Data Index: 784037 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.6715. Min Act: -0.1700
Data Index: 453052 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.6715. Min Act: -0.1700
Data Index: 3079815 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9840. Min Range: -7.9840
Max Act: 7.6715. Min Act: -0.1700
Data Index: 3044556 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19