Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2735. Min Range: -5.2735
Max Act: 5.2735. Min Act: -0.1700
Data Index: 6106931 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2735. Min Range: -5.2735
Max Act: 5.2110. Min Act: -0.1700
Data Index: 4257473 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2735. Min Range: -5.2735
Max Act: 5.1797. Min Act: -0.1700
Data Index: 5321053 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2735. Min Range: -5.2735
Max Act: 5.1797. Min Act: -0.1700
Data Index: 3368031 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2735. Min Range: -5.2735
Max Act: 5.0547. Min Act: -0.1700
Data Index: 1657859 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2735. Min Range: -5.2735
Max Act: 5.0547. Min Act: -0.1700
Data Index: 771588 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2735. Min Range: -5.2735
Max Act: 5.0235. Min Act: -0.1700
Data Index: 894811 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2735. Min Range: -5.2735
Max Act: 5.0547. Min Act: -0.1700
Data Index: 500473 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.9922. Min Act: -0.1700
Data Index: 1049028 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.9610. Min Act: -0.1700
Data Index: 4096426 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.9610. Min Act: -0.1700
Data Index: 6765393 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.9610. Min Act: -0.1700
Data Index: 684562 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.9610. Min Act: -0.1700
Data Index: 141775 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.9297. Min Act: -0.1700
Data Index: 964726 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.9297. Min Act: -0.1700
Data Index: 4735960 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.8672. Min Act: -0.1700
Data Index: 6178739 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.8985. Min Act: -0.1700
Data Index: 2463865 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.8985. Min Act: -0.1700
Data Index: 4885372 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.8985. Min Act: -0.1700
Data Index: 3431401 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2735. Min Range: -5.2735
Max Act: 4.8672. Min Act: -0.1700
Data Index: 4179523 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19