Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1430 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.6106. Min Act: -0.1700
Data Index: 2472772 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.4543. Min Act: -0.1700
Data Index: 984122 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.2668. Min Act: -0.1700
Data Index: 3869580 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.2043. Min Act: -0.1700
Data Index: 171041 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.2043. Min Act: -0.1700
Data Index: 8000040 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.2356. Min Act: -0.1700
Data Index: 1761455 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.1418. Min Act: -0.1700
Data Index: 7762999 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.1418. Min Act: -0.1700
Data Index: 31079 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.1418. Min Act: -0.1700
Data Index: 4040537 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.1106. Min Act: -0.1700
Data Index: 7458831 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.1106. Min Act: -0.1700
Data Index: 1297881 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.1106. Min Act: -0.1700
Data Index: 1280520 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.0793. Min Act: -0.1700
Data Index: 3730792 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.0793. Min Act: -0.1700
Data Index: 3144598 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.0481. Min Act: -0.1700
Data Index: 8372002 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.0168. Min Act: -0.1700
Data Index: 5843121 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.0481. Min Act: -0.1700
Data Index: 6205123 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.0168. Min Act: -0.1700
Data Index: 6305448 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.0481. Min Act: -0.1700
Data Index: 8554983 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6106. Min Range: -5.6106
Max Act: 5.0168. Min Act: -0.1700
Data Index: 4888558 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19