Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.4537. Min Act: -0.1700
Data Index: 1064174 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.4225. Min Act: -0.1700
Data Index: 8825774 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.4537. Min Act: -0.1700
Data Index: 5841303 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3912. Min Act: -0.1700
Data Index: 5358190 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3912. Min Act: -0.1700
Data Index: 3394808 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3912. Min Act: -0.1700
Data Index: 5533177 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3600. Min Act: -0.1700
Data Index: 3309326 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3287. Min Act: -0.1700
Data Index: 1064175 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3287. Min Act: -0.1700
Data Index: 1369120 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3287. Min Act: -0.1700
Data Index: 8530083 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3287. Min Act: -0.1700
Data Index: 3906708 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.2975. Min Act: -0.1700
Data Index: 8530081 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.3287. Min Act: -0.1700
Data Index: 6613094 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.2975. Min Act: -0.1700
Data Index: 6970872 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.2975. Min Act: -0.1700
Data Index: 7688578 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.2975. Min Act: -0.1700
Data Index: 589369 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.2662. Min Act: -0.1700
Data Index: 2102199 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.2350. Min Act: -0.1700
Data Index: 136193 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.2662. Min Act: -0.1700
Data Index: 2157234 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4537. Min Range: -6.4537
Max Act: 6.2662. Min Act: -0.1700
Data Index: 4009632 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19