Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.4883. Min Act: -0.1700
Data Index: 91307 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.4570. Min Act: -0.1700
Data Index: 479237 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.4257. Min Act: -0.1700
Data Index: 2400570 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.3320. Min Act: -0.1700
Data Index: 4539290 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.2070. Min Act: -0.1700
Data Index: 317556 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.2070. Min Act: -0.1700
Data Index: 6935077 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.2070. Min Act: -0.1700
Data Index: 3398715 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.1757. Min Act: -0.1700
Data Index: 6748430 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.1445. Min Act: -0.1700
Data Index: 534797 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.1445. Min Act: -0.1700
Data Index: 5314135 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.0820. Min Act: -0.1700
Data Index: 2614924 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.1132. Min Act: -0.1700
Data Index: 7479136 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.1132. Min Act: -0.1700
Data Index: 2920167 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.1132. Min Act: -0.1700
Data Index: 2011042 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.1132. Min Act: -0.1700
Data Index: 8251487 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.0820. Min Act: -0.1700
Data Index: 3447260 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.0820. Min Act: -0.1700
Data Index: 5928150 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.0820. Min Act: -0.1700
Data Index: 2867729 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.0820. Min Act: -0.1700
Data Index: 523444 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4883. Min Range: -4.4883
Max Act: 4.0507. Min Act: -0.1700
Data Index: 959444 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19