Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.6206. Min Act: -0.1700
Data Index: 662920 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.5581. Min Act: -0.1700
Data Index: 4088740 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.4956. Min Act: -0.1700
Data Index: 4601239 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.4643. Min Act: -0.1700
Data Index: 3048503 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.3393. Min Act: -0.1700
Data Index: 2272248 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.3081. Min Act: -0.1700
Data Index: 8430481 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.2768. Min Act: -0.1700
Data Index: 2981633 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.2143. Min Act: -0.1700
Data Index: 6168109 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.2143. Min Act: -0.1700
Data Index: 8528023 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1831. Min Act: -0.1700
Data Index: 2025244 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1831. Min Act: -0.1700
Data Index: 1807027 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1518. Min Act: -0.1700
Data Index: 656156 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1206. Min Act: -0.1700
Data Index: 1850596 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1518. Min Act: -0.1700
Data Index: 4892698 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1206. Min Act: -0.1700
Data Index: 3676035 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1206. Min Act: -0.1700
Data Index: 7681528 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1206. Min Act: -0.1700
Data Index: 5278182 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.1206. Min Act: -0.1700
Data Index: 1260456 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.0893. Min Act: -0.1700
Data Index: 4273087 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6206. Min Range: -6.6206
Max Act: 6.0893. Min Act: -0.1700
Data Index: 5948242 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19