Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 102 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.9736. Min Act: -0.1700
Data Index: 2682639 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.3486. Min Act: -0.1700
Data Index: 3800044 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.2549. Min Act: -0.1700
Data Index: 1396106 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.2549. Min Act: -0.1700
Data Index: 1561254 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.1299. Min Act: -0.1700
Data Index: 926425 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.1611. Min Act: -0.1700
Data Index: 6614987 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.1611. Min Act: -0.1700
Data Index: 5893126 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0986. Min Act: -0.1700
Data Index: 6718777 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0674. Min Act: -0.1700
Data Index: 7831886 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0674. Min Act: -0.1700
Data Index: 8786909 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0674. Min Act: -0.1700
Data Index: 7763105 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0361. Min Act: -0.1700
Data Index: 2304748 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0049. Min Act: -0.1700
Data Index: 1860448 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0674. Min Act: -0.1700
Data Index: 7526583 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0049. Min Act: -0.1700
Data Index: 6649031 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9736. Min Range: -6.9736
Max Act: 5.9736. Min Act: -0.1700
Data Index: 4113843 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0049. Min Act: -0.1700
Data Index: 4406881 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9736. Min Range: -6.9736
Max Act: 6.0049. Min Act: -0.1700
Data Index: 3250106 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9736. Min Range: -6.9736
Max Act: 5.9736. Min Act: -0.1700
Data Index: 611285 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9736. Min Range: -6.9736
Max Act: 5.9736. Min Act: -0.1700
Data Index: 5076961 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19