Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1945 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0487. Min Range: -7.0487
Max Act: 7.0487. Min Act: -0.1700
Data Index: 340359 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.9862. Min Act: -0.1700
Data Index: 2082100 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.9862. Min Act: -0.1700
Data Index: 6150472 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.8925. Min Act: -0.1700
Data Index: 6150462 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.6737. Min Act: -0.1700
Data Index: 8830422 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.6112. Min Act: -0.1700
Data Index: 1409799 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.5175. Min Act: -0.1700
Data Index: 6763882 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.5175. Min Act: -0.1700
Data Index: 4227754 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.4862. Min Act: -0.1700
Data Index: 4401192 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.5487. Min Act: -0.1700
Data Index: 6683268 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.4550. Min Act: -0.1700
Data Index: 6821987 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.4550. Min Act: -0.1700
Data Index: 5137063 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.4550. Min Act: -0.1700
Data Index: 4998990 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.3925. Min Act: -0.1700
Data Index: 5576763 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.3925. Min Act: -0.1700
Data Index: 4690375 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.4237. Min Act: -0.1700
Data Index: 5934556 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.2987. Min Act: -0.1700
Data Index: 2927107 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.2987. Min Act: -0.1700
Data Index: 7663208 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.3300. Min Act: -0.1700
Data Index: 869775 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0487. Min Range: -7.0487
Max Act: 6.2675. Min Act: -0.1700
Data Index: 6795014 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19