Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1848 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4518. Min Range: -9.4518
Max Act: 9.4518. Min Act: -0.1700
Data Index: 2910672 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4518. Min Range: -9.4518
Max Act: 9.2018. Min Act: -0.1700
Data Index: 1368362 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4518. Min Range: -9.4518
Max Act: 9.2018. Min Act: -0.1700
Data Index: 5129789 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4518. Min Range: -9.4518
Max Act: 9.0768. Min Act: -0.1700
Data Index: 1146183 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.8893. Min Act: -0.1700
Data Index: 6143202 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.8893. Min Act: -0.1700
Data Index: 296136 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.8893. Min Act: -0.1700
Data Index: 8561181 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.7643. Min Act: -0.1700
Data Index: 2534187 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.6393. Min Act: -0.1700
Data Index: 1398450 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.6393. Min Act: -0.1700
Data Index: 5446927 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.6393. Min Act: -0.1700
Data Index: 5689071 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.6393. Min Act: -0.1700
Data Index: 3172923 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.7018. Min Act: -0.1700
Data Index: 5897447 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.7018. Min Act: -0.1700
Data Index: 7250057 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.5768. Min Act: -0.1700
Data Index: 3409600 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.5768. Min Act: -0.1699
Data Index: 370420 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.5768. Min Act: -0.1700
Data Index: 4713949 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.5143. Min Act: -0.1700
Data Index: 4288033 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.5768. Min Act: -0.1700
Data Index: 2035864 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4518. Min Range: -9.4518
Max Act: 8.5143. Min Act: -0.1700
Data Index: 524419 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19