Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4468. Min Range: -9.4468
Max Act: 9.4468. Min Act: -0.1700
Data Index: 2733210 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4468. Min Range: -9.4468
Max Act: 9.4468. Min Act: -0.1700
Data Index: 453923 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4468. Min Range: -9.4468
Max Act: 9.1968. Min Act: -0.1700
Data Index: 3086336 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4468. Min Range: -9.4468
Max Act: 9.1968. Min Act: -0.1700
Data Index: 2068849 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4468. Min Range: -9.4468
Max Act: 9.1968. Min Act: -0.1700
Data Index: 8566677 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4468. Min Range: -9.4468
Max Act: 9.0093. Min Act: -0.1700
Data Index: 5836960 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.9468. Min Act: -0.1700
Data Index: 1587770 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.9468. Min Act: -0.1700
Data Index: 7364112 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.9468. Min Act: -0.1700
Data Index: 7520408 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.9468. Min Act: -0.1700
Data Index: 8516324 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.8843. Min Act: -0.1700
Data Index: 1967868 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.9468. Min Act: -0.1700
Data Index: 1106964 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.9468. Min Act: -0.1700
Data Index: 413079 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.8843. Min Act: -0.1700
Data Index: 24311 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.7593. Min Act: -0.1700
Data Index: 5151330 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.8218. Min Act: -0.1700
Data Index: 4860405 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.8843. Min Act: -0.1700
Data Index: 460292 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.8218. Min Act: -0.1700
Data Index: 3462508 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.8218. Min Act: -0.1700
Data Index: 575298 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4468. Min Range: -9.4468
Max Act: 8.7593. Min Act: -0.1700
Data Index: 5194866 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19