Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4500 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.7038. Min Act: -0.1700
Data Index: 2326706 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.7038. Min Act: -0.1700
Data Index: 1318602 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.6725. Min Act: -0.1700
Data Index: 4046453 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.5788. Min Act: -0.1700
Data Index: 7868283 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.4850. Min Act: -0.1700
Data Index: 8706523 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.4538. Min Act: -0.1700
Data Index: 1021523 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.4538. Min Act: -0.1700
Data Index: 4180499 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.4225. Min Act: -0.1700
Data Index: 585141 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.4225. Min Act: -0.1700
Data Index: 1623613 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.4225. Min Act: -0.1700
Data Index: 7168619 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.4225. Min Act: -0.1700
Data Index: 6568598 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3913. Min Act: -0.1700
Data Index: 2186409 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3913. Min Act: -0.1700
Data Index: 2326707 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3913. Min Act: -0.1700
Data Index: 4737336 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3913. Min Act: -0.1700
Data Index: 8248123 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3913. Min Act: -0.1700
Data Index: 2186411 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3600. Min Act: -0.1700
Data Index: 262178 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3913. Min Act: -0.1700
Data Index: 3954406 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3600. Min Act: -0.1700
Data Index: 5152748 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7038. Min Range: -4.7038
Max Act: 4.3600. Min Act: -0.1700
Data Index: 619768 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19