Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6871. Min Range: -7.6871
Max Act: 7.6871. Min Act: -0.1700
Data Index: 864056 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6871. Min Range: -7.6871
Max Act: 7.3746. Min Act: -0.1700
Data Index: 5646509 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6871. Min Range: -7.6871
Max Act: 7.1871. Min Act: -0.1700
Data Index: 8256758 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6871. Min Range: -7.6871
Max Act: 7.1871. Min Act: -0.1700
Data Index: 4557755 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6871. Min Range: -7.6871
Max Act: 7.0933. Min Act: -0.1700
Data Index: 6026105 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6871. Min Range: -7.6871
Max Act: 7.0621. Min Act: -0.1700
Data Index: 5271704 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6871. Min Range: -7.6871
Max Act: 7.0308. Min Act: -0.1700
Data Index: 6011467 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.9996. Min Act: -0.1700
Data Index: 8443782 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.9996. Min Act: -0.1700
Data Index: 203254 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.9371. Min Act: -0.1700
Data Index: 2013682 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.9371. Min Act: -0.1700
Data Index: 8365200 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.9683. Min Act: -0.1700
Data Index: 1090713 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.9371. Min Act: -0.1700
Data Index: 371028 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.9058. Min Act: -0.1700
Data Index: 165295 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.9371. Min Act: -0.1700
Data Index: 2685923 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.8433. Min Act: -0.1700
Data Index: 2962264 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.8746. Min Act: -0.1700
Data Index: 7490382 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.8746. Min Act: -0.1700
Data Index: 7862269 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.8746. Min Act: -0.1700
Data Index: 3448192 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6871. Min Range: -7.6871
Max Act: 6.8433. Min Act: -0.1700
Data Index: 1043166 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19