Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.9174. Min Act: -0.1700
Data Index: 4599333 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.8747. Min Act: -0.1700
Data Index: 1998801 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.8062. Min Act: -0.1700
Data Index: 8678573 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.8147. Min Act: -0.1700
Data Index: 2907684 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.8062. Min Act: -0.1700
Data Index: 4174877 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7803. Min Act: -0.1700
Data Index: 837104 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7889. Min Act: -0.1700
Data Index: 1606841 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7889. Min Act: -0.1700
Data Index: 8144203 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7631. Min Act: -0.1699
Data Index: 4963252 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7545. Min Act: -0.1697
Data Index: 2198299 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7458. Min Act: -0.1700
Data Index: 7140640 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7458. Min Act: -0.1700
Data Index: 7831058 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7285. Min Act: -0.1700
Data Index: 7277600 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7372. Min Act: -0.1700
Data Index: 4255003 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7285. Min Act: -0.1700
Data Index: 6289151 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7199. Min Act: -0.1700
Data Index: 2037117 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7285. Min Act: -0.1700
Data Index: 6599259 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7285. Min Act: -0.1700
Data Index: 3084095 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7112. Min Act: -0.1699
Data Index: 494200 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9174. Min Range: -1.9174
Max Act: 1.7199. Min Act: -0.1700
Data Index: 7961146 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19