Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2384 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.9745. Min Act: -0.1700
Data Index: 2580059 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.8183. Min Act: -0.1700
Data Index: 2699867 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.6933. Min Act: -0.1700
Data Index: 5832534 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.6933. Min Act: -0.1700
Data Index: 7654648 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.6933. Min Act: -0.1700
Data Index: 1384992 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.6308. Min Act: -0.1700
Data Index: 3842231 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.6620. Min Act: -0.1700
Data Index: 3954670 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5995. Min Act: -0.1700
Data Index: 8617653 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1725389 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5683. Min Act: -0.1700
Data Index: 5685682 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5683. Min Act: -0.1700
Data Index: 7708029 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5370. Min Act: -0.1700
Data Index: 6178444 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5058. Min Act: -0.1700
Data Index: 8316053 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5058. Min Act: -0.1700
Data Index: 8550585 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5058. Min Act: -0.1700
Data Index: 5109736 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.5058. Min Act: -0.1700
Data Index: 1827264 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.4745. Min Act: -0.1700
Data Index: 6874860 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.4745. Min Act: -0.1700
Data Index: 1985724 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.4745. Min Act: -0.1700
Data Index: 8635807 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9745. Min Range: -5.9745
Max Act: 5.4745. Min Act: -0.1700
Data Index: 3530243 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19