Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2273 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0784. Min Range: -7.0784
Max Act: 7.0784. Min Act: -0.1700
Data Index: 8169459 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.9847. Min Act: -0.1700
Data Index: 6689475 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.9222. Min Act: -0.1700
Data Index: 3979109 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.8284. Min Act: -0.1700
Data Index: 8333072 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.7972. Min Act: -0.1700
Data Index: 5213396 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.7034. Min Act: -0.1700
Data Index: 7477289 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.6097. Min Act: -0.1700
Data Index: 8366010 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.4847. Min Act: -0.1700
Data Index: 4906145 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.4534. Min Act: -0.1700
Data Index: 6222404 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.4534. Min Act: -0.1700
Data Index: 5420992 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.4222. Min Act: -0.1700
Data Index: 8168655 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.3597. Min Act: -0.1700
Data Index: 4082247 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.3597. Min Act: -0.1700
Data Index: 3921616 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.3597. Min Act: -0.1700
Data Index: 8412442 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.3597. Min Act: -0.1700
Data Index: 8717515 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.3597. Min Act: -0.1700
Data Index: 4175974 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.3597. Min Act: -0.1700
Data Index: 5012848 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.3597. Min Act: -0.1700
Data Index: 5629141 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.2972. Min Act: -0.1700
Data Index: 2713469 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0784. Min Range: -7.0784
Max Act: 6.2972. Min Act: -0.1700
Data Index: 7867566 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19