Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1916. Min Range: -7.1916
Max Act: 7.1916. Min Act: -0.1700
Data Index: 7454006 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1916. Min Range: -7.1916
Max Act: 7.1604. Min Act: -0.1700
Data Index: 8780305 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1916. Min Range: -7.1916
Max Act: 7.0979. Min Act: -0.1700
Data Index: 8382477 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1916. Min Range: -7.1916
Max Act: 7.0979. Min Act: -0.1700
Data Index: 7572061 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1916. Min Range: -7.1916
Max Act: 7.0041. Min Act: -0.1700
Data Index: 217548 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.9729. Min Act: -0.1700
Data Index: 7811909 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1916. Min Range: -7.1916
Max Act: 7.0041. Min Act: -0.1700
Data Index: 7519706 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1916. Min Range: -7.1916
Max Act: 7.0041. Min Act: -0.1700
Data Index: 5447229 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.9729. Min Act: -0.1700
Data Index: 3812980 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.9416. Min Act: -0.1700
Data Index: 8813818 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.9104. Min Act: -0.1700
Data Index: 7550519 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.9104. Min Act: -0.1700
Data Index: 8284150 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.8479. Min Act: -0.1700
Data Index: 2596836 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.8791. Min Act: -0.1700
Data Index: 4861826 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.8791. Min Act: -0.1700
Data Index: 7803673 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.8791. Min Act: -0.1700
Data Index: 602844 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.8479. Min Act: -0.1700
Data Index: 6236320 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.8479. Min Act: -0.1700
Data Index: 4531483 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.8166. Min Act: -0.1700
Data Index: 154947 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1916. Min Range: -7.1916
Max Act: 6.7854. Min Act: -0.1700
Data Index: 4949009 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19