Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 936 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0647. Min Act: -0.1700
Data Index: 2851931 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0479. Min Act: -0.1700
Data Index: 2719945 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0479. Min Act: -0.1700
Data Index: 1188985 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0479. Min Act: -0.1700
Data Index: 2857234 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0310. Min Act: -0.1700
Data Index: 6576106 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0310. Min Act: -0.1700
Data Index: 3325070 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0142. Min Act: -0.1700
Data Index: 3632383 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1700
Data Index: 8642409 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1700
Data Index: 280544 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1700
Data Index: 2807534 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0142. Min Act: -0.1700
Data Index: 8496002 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1700
Data Index: 6640952 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9804. Min Act: -0.1700
Data Index: 2237924 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1700
Data Index: 107919 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1700
Data Index: 7973125 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9804. Min Act: -0.1700
Data Index: 7883068 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1700
Data Index: 4035202 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1700
Data Index: 1772601 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0647. Min Range: -2.0647
Max Act: 2.0142. Min Act: -0.1700
Data Index: 6591696 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0647. Min Range: -2.0647
Max Act: 1.9973. Min Act: -0.1699
Data Index: 1586429 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19