Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.2345. Min Act: -0.1700
Data Index: 1654217 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.2179. Min Act: -0.1700
Data Index: 2187545 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.1515. Min Act: -0.1700
Data Index: 2319311 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.0846. Min Act: -0.1700
Data Index: 1466334 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.1013. Min Act: -0.1700
Data Index: 4014811 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.0678. Min Act: -0.1700
Data Index: 2285448 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.0510. Min Act: -0.1700
Data Index: 2498410 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.0004. Min Act: -0.1700
Data Index: 5610138 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.0004. Min Act: -0.1700
Data Index: 7714755 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.0004. Min Act: -0.1700
Data Index: 5614105 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2345. Min Range: -2.2345
Max Act: 2.0004. Min Act: -0.1700
Data Index: 4019395 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9835. Min Act: -0.1700
Data Index: 4733613 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9835. Min Act: -0.1700
Data Index: 7062446 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9496. Min Act: -0.1700
Data Index: 6950118 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9666. Min Act: -0.1700
Data Index: 5892119 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9835. Min Act: -0.1700
Data Index: 7753199 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9326. Min Act: -0.1700
Data Index: 5271368 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9326. Min Act: -0.1700
Data Index: 5284218 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9326. Min Act: -0.1700
Data Index: 1906087 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2345. Min Range: -2.2345
Max Act: 1.9326. Min Act: -0.1700
Data Index: 1654216 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19