Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.5166. Min Act: -0.1700
Data Index: 5632416 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.3916. Min Act: -0.1700
Data Index: 375128 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.3291. Min Act: -0.1700
Data Index: 3591636 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.2979. Min Act: -0.1699
Data Index: 593943 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.2979. Min Act: -0.1700
Data Index: 7591727 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.2979. Min Act: -0.1700
Data Index: 3773974 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.2354. Min Act: -0.1700
Data Index: 1763374 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.1729. Min Act: -0.1700
Data Index: 5079002 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.1416. Min Act: -0.1700
Data Index: 6065959 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.1104. Min Act: -0.1700
Data Index: 6166712 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.1104. Min Act: -0.1700
Data Index: 5271450 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0791. Min Act: -0.1700
Data Index: 4099315 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0791. Min Act: -0.1700
Data Index: 1538674 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0791. Min Act: -0.1700
Data Index: 7732368 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0791. Min Act: -0.1700
Data Index: 830355 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0166. Min Act: -0.1700
Data Index: 7899253 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0479. Min Act: -0.1700
Data Index: 8055593 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0166. Min Act: -0.1700
Data Index: 4277018 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0166. Min Act: -0.1700
Data Index: 2716458 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5166. Min Range: -7.5166
Max Act: 7.0166. Min Act: -0.1700
Data Index: 1940162 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19