Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.8825. Min Act: -0.1700
Data Index: 4445404 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.6950. Min Act: -0.1700
Data Index: 4753606 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.6638. Min Act: -0.1700
Data Index: 8038849 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.6013. Min Act: -0.1700
Data Index: 539538 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5700. Min Act: -0.1700
Data Index: 6576010 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5700. Min Act: -0.1700
Data Index: 266758 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5700. Min Act: -0.1700
Data Index: 5647761 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5388. Min Act: -0.1700
Data Index: 7217777 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5388. Min Act: -0.1700
Data Index: 4146224 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5388. Min Act: -0.1700
Data Index: 8701499 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5075. Min Act: -0.1700
Data Index: 8049242 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5075. Min Act: -0.1700
Data Index: 4280155 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5075. Min Act: -0.1700
Data Index: 8231259 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.5075. Min Act: -0.1700
Data Index: 13877 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.4450. Min Act: -0.1700
Data Index: 5436873 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.4450. Min Act: -0.1700
Data Index: 3899969 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.4450. Min Act: -0.1700
Data Index: 367542 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.4138. Min Act: -0.1700
Data Index: 4389603 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.4138. Min Act: -0.1700
Data Index: 2680155 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8825. Min Range: -4.8825
Max Act: 4.3825. Min Act: -0.1700
Data Index: 8142041 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19