Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.7277. Min Act: -0.1700
Data Index: 6926161 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.7277. Min Act: -0.1700
Data Index: 7736644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.6340. Min Act: -0.1700
Data Index: 8249221 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.6652. Min Act: -0.1700
Data Index: 4287398 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.6340. Min Act: -0.1700
Data Index: 6224104 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.6027. Min Act: -0.1700
Data Index: 1316854 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.6027. Min Act: -0.1700
Data Index: 1133556 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4465. Min Act: -0.1700
Data Index: 4095701 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4465. Min Act: -0.1700
Data Index: 3018371 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4777. Min Act: -0.1700
Data Index: 1660295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4777. Min Act: -0.1700
Data Index: 5520090 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4777. Min Act: -0.1700
Data Index: 7366327 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4152. Min Act: -0.1700
Data Index: 5156794 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4152. Min Act: -0.1700
Data Index: 5152359 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4152. Min Act: -0.1700
Data Index: 7189286 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.3840. Min Act: -0.1700
Data Index: 4095700 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.3840. Min Act: -0.1700
Data Index: 6034214 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.3840. Min Act: -0.1700
Data Index: 4262723 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.4152. Min Act: -0.1700
Data Index: 4207668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7277. Min Range: -4.7277
Max Act: 4.3527. Min Act: -0.1700
Data Index: 4429023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19