Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1697 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.5690. Min Act: -0.1700
Data Index: 3953453 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.6003. Min Act: -0.1700
Data Index: 965331 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.6003. Min Act: -0.1700
Data Index: 5985191 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.5690. Min Act: -0.1700
Data Index: 7880741 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.5690. Min Act: -0.1700
Data Index: 690494 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.5378. Min Act: -0.1700
Data Index: 6068495 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.5378. Min Act: -0.1700
Data Index: 7633098 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6913033 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.4753. Min Act: -0.1700
Data Index: 2419562 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.4440. Min Act: -0.1700
Data Index: 4278944 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.4440. Min Act: -0.1700
Data Index: 4623346 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.4440. Min Act: -0.1700
Data Index: 4623340 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6207646 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.4128. Min Act: -0.1700
Data Index: 4623333 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.4128. Min Act: -0.1700
Data Index: 7562282 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.3815. Min Act: -0.1700
Data Index: 4166049 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.3503. Min Act: -0.1700
Data Index: 696144 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.3503. Min Act: -0.1700
Data Index: 7154799 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.3503. Min Act: -0.1700
Data Index: 1952643 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6003. Min Range: -5.6003
Max Act: 5.3503. Min Act: -0.1700
Data Index: 7231240 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19