Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5467 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0791. Min Range: -8.0791
Max Act: 8.0791. Min Act: -0.1700
Data Index: 1207440 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0791. Min Range: -8.0791
Max Act: 7.9854. Min Act: -0.1700
Data Index: 3184714 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0791. Min Range: -8.0791
Max Act: 7.8604. Min Act: -0.1700
Data Index: 7771089 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0791. Min Range: -8.0791
Max Act: 7.5791. Min Act: -0.1700
Data Index: 6678550 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0791. Min Range: -8.0791
Max Act: 7.4541. Min Act: -0.1700
Data Index: 8266418 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0791. Min Range: -8.0791
Max Act: 7.3291. Min Act: -0.1700
Data Index: 3083320 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0791. Min Range: -8.0791
Max Act: 7.1729. Min Act: -0.1700
Data Index: 3082407 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0791. Min Range: -8.0791
Max Act: 7.0479. Min Act: -0.1700
Data Index: 2693713 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0791. Min Range: -8.0791
Max Act: 7.0166. Min Act: -0.1700
Data Index: 4907031 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.9229. Min Act: -0.1700
Data Index: 8686056 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.9229. Min Act: -0.1700
Data Index: 1483664 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.8916. Min Act: -0.1700
Data Index: 6062765 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.8604. Min Act: -0.1700
Data Index: 44612 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.8291. Min Act: -0.1700
Data Index: 6085839 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.7979. Min Act: -0.1700
Data Index: 7734247 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.7666. Min Act: -0.1700
Data Index: 3869289 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.7666. Min Act: -0.1700
Data Index: 4838608 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.7354. Min Act: -0.1700
Data Index: 8539359 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.7666. Min Act: -0.1700
Data Index: 5489074 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0791. Min Range: -8.0791
Max Act: 6.7666. Min Act: -0.1700
Data Index: 472609 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19