Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5212 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.8163. Min Act: -0.1700
Data Index: 3650374 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.8163. Min Act: -0.1700
Data Index: 3357638 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.5663. Min Act: -0.1700
Data Index: 811880 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.4100. Min Act: -0.1700
Data Index: 2834159 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.3475. Min Act: -0.1700
Data Index: 2945157 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.3163. Min Act: -0.1700
Data Index: 1932392 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.3475. Min Act: -0.1700
Data Index: 1537183 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.3475. Min Act: -0.1700
Data Index: 5065553 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.3163. Min Act: -0.1700
Data Index: 981543 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.3163. Min Act: -0.1700
Data Index: 6635732 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.3163. Min Act: -0.1700
Data Index: 5036331 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2850. Min Act: -0.1700
Data Index: 8443570 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2850. Min Act: -0.1700
Data Index: 4853129 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2850. Min Act: -0.1700
Data Index: 1959210 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6092078 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2538. Min Act: -0.1700
Data Index: 5949255 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2538. Min Act: -0.1700
Data Index: 6845252 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2225. Min Act: -0.1700
Data Index: 2709959 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2225. Min Act: -0.1700
Data Index: 290028 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8163. Min Range: -6.8163
Max Act: 6.2225. Min Act: -0.1700
Data Index: 1319528 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19