Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.2384. Min Act: -0.1700
Data Index: 2939435 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.2384. Min Act: -0.1700
Data Index: 4202169 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.2227. Min Act: -0.1700
Data Index: 6237262 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.1598. Min Act: -0.1700
Data Index: 5699926 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.1598. Min Act: -0.1700
Data Index: 955898 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.1283. Min Act: -0.1700
Data Index: 2195589 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.1283. Min Act: -0.1700
Data Index: 7178326 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.0810. Min Act: -0.1700
Data Index: 3459232 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.1126. Min Act: -0.1700
Data Index: 5464439 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.0337. Min Act: -0.1700
Data Index: 6850215 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.0179. Min Act: -0.1700
Data Index: 6188842 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.0179. Min Act: -0.1700
Data Index: 5952779 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2384. Min Range: -3.2384
Max Act: 3.0021. Min Act: -0.1700
Data Index: 6483364 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2384. Min Range: -3.2384
Max Act: 2.9863. Min Act: -0.1700
Data Index: 6055634 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2384. Min Range: -3.2384
Max Act: 2.9705. Min Act: -0.1700
Data Index: 6668725 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2384. Min Range: -3.2384
Max Act: 2.9863. Min Act: -0.1700
Data Index: 1768451 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2384. Min Range: -3.2384
Max Act: 2.9547. Min Act: -0.1700
Data Index: 8281087 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2384. Min Range: -3.2384
Max Act: 2.9863. Min Act: -0.1700
Data Index: 3796722 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2384. Min Range: -3.2384
Max Act: 2.9547. Min Act: -0.1700
Data Index: 5251244 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2384. Min Range: -3.2384
Max Act: 2.9705. Min Act: -0.1700
Data Index: 4601166 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19