Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.2156. Min Act: -0.1700
Data Index: 4507325 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.2156. Min Act: -0.1700
Data Index: 8238652 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.2156. Min Act: -0.1700
Data Index: 3638234 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1841. Min Act: -0.1700
Data Index: 6369023 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.2156. Min Act: -0.1700
Data Index: 4895587 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1841. Min Act: -0.1700
Data Index: 3646357 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1841. Min Act: -0.1700
Data Index: 158054 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1841. Min Act: -0.1700
Data Index: 2665000 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1841. Min Act: -0.1700
Data Index: 5499996 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1841. Min Act: -0.1700
Data Index: 3614007 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 565758 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 1850773 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 1624511 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 3095441 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 1877879 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 2948215 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 4485420 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 1947224 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 5036134 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2156. Min Range: -3.2156
Max Act: 3.1526. Min Act: -0.1700
Data Index: 5402589 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19