Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.7187. Min Act: -0.1700
Data Index: 4113128 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.6874. Min Act: -0.1700
Data Index: 7383277 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.6562. Min Act: -0.1700
Data Index: 1698158 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.5624. Min Act: -0.1698
Data Index: 6073945 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.5937. Min Act: -0.1700
Data Index: 7011673 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.5312. Min Act: -0.1699
Data Index: 3334707 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.5312. Min Act: -0.1700
Data Index: 789580 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4999. Min Act: -0.1700
Data Index: 1725444 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4999. Min Act: -0.1700
Data Index: 6440544 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4999. Min Act: -0.1700
Data Index: 6192963 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4687. Min Act: -0.1700
Data Index: 4165889 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4687. Min Act: -0.1700
Data Index: 2345448 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4687. Min Act: -0.1700
Data Index: 1221224 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4374. Min Act: -0.1700
Data Index: 1916555 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4374. Min Act: -0.1700
Data Index: 8252643 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4062. Min Act: -0.1700
Data Index: 2345449 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4062. Min Act: -0.1700
Data Index: 7099912 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.4062. Min Act: -0.1700
Data Index: 7974203 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.3749. Min Act: -0.1700
Data Index: 4613266 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7187. Min Range: -6.7187
Max Act: 6.3749. Min Act: -0.1700
Data Index: 3353264 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19