Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.6105. Min Act: -0.1700
Data Index: 6546845 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.4543. Min Act: -0.1700
Data Index: 2552471 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.3918. Min Act: -0.1700
Data Index: 8697540 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.3605. Min Act: -0.1700
Data Index: 1513950 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.3918. Min Act: -0.1700
Data Index: 6293576 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.3605. Min Act: -0.1700
Data Index: 377571 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.3293. Min Act: -0.1700
Data Index: 3290327 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.3293. Min Act: -0.1700
Data Index: 6003531 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2980. Min Act: -0.1700
Data Index: 413791 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2980. Min Act: -0.1700
Data Index: 407666 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2980. Min Act: -0.1700
Data Index: 1024901 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2980. Min Act: -0.1700
Data Index: 2552461 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2980. Min Act: -0.1700
Data Index: 4439263 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2668. Min Act: -0.1700
Data Index: 5048720 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2355. Min Act: -0.1700
Data Index: 4458248 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2355. Min Act: -0.1700
Data Index: 1443144 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2668. Min Act: -0.1700
Data Index: 8401527 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2668. Min Act: -0.1700
Data Index: 392310 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2043. Min Act: -0.1700
Data Index: 7959595 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6105. Min Range: -4.6105
Max Act: 4.2355. Min Act: -0.1700
Data Index: 5044830 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19