Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 862 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.9487. Min Act: -0.1700
Data Index: 7541411 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.6050. Min Act: -0.1700
Data Index: 1013977 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.3550. Min Act: -0.1700
Data Index: 577648 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.3237. Min Act: -0.1700
Data Index: 2120177 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.2612. Min Act: -0.1700
Data Index: 6882179 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.2612. Min Act: -0.1700
Data Index: 489856 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.1987. Min Act: -0.1700
Data Index: 7763300 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.1987. Min Act: -0.1700
Data Index: 7847121 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.1050. Min Act: -0.1700
Data Index: 5602968 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.1050. Min Act: -0.1700
Data Index: 96622 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.0737. Min Act: -0.1700
Data Index: 3528170 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.0425. Min Act: -0.1700
Data Index: 6399503 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.0112. Min Act: -0.1700
Data Index: 892081 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.0112. Min Act: -0.1700
Data Index: 1725665 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9487. Min Range: -7.9487
Max Act: 7.0112. Min Act: -0.1700
Data Index: 3607386 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9487. Min Range: -7.9487
Max Act: 6.9487. Min Act: -0.1700
Data Index: 6513632 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9487. Min Range: -7.9487
Max Act: 6.9175. Min Act: -0.1700
Data Index: 3911747 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9487. Min Range: -7.9487
Max Act: 6.8862. Min Act: -0.1700
Data Index: 852637 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9487. Min Range: -7.9487
Max Act: 6.8862. Min Act: -0.1700
Data Index: 3972738 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9487. Min Range: -7.9487
Max Act: 6.7925. Min Act: -0.1700
Data Index: 802341 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19