Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0932. Min Range: -4.0932
Max Act: 4.0932. Min Act: -0.1700
Data Index: 3760434 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0932. Min Range: -4.0932
Max Act: 4.0307. Min Act: -0.1700
Data Index: 95892 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9994. Min Act: -0.1700
Data Index: 8306521 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9994. Min Act: -0.1700
Data Index: 6946312 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9682. Min Act: -0.1700
Data Index: 1974530 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9682. Min Act: -0.1700
Data Index: 3478971 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9994. Min Act: -0.1700
Data Index: 7882236 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9994. Min Act: -0.1700
Data Index: 7482768 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9369. Min Act: -0.1700
Data Index: 1086518 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9056. Min Act: -0.1700
Data Index: 3821638 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9369. Min Act: -0.1700
Data Index: 1502265 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9369. Min Act: -0.1700
Data Index: 5116847 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9056. Min Act: -0.1700
Data Index: 6572085 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9056. Min Act: -0.1700
Data Index: 3484018 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.9056. Min Act: -0.1700
Data Index: 1328796 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.8744. Min Act: -0.1700
Data Index: 1897659 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.8431. Min Act: -0.1700
Data Index: 271905 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.8744. Min Act: -0.1700
Data Index: 1070291 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.8744. Min Act: -0.1700
Data Index: 7059177 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0932. Min Range: -4.0932
Max Act: 3.8744. Min Act: -0.1700
Data Index: 5992553 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19