Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5964. Min Range: -8.5964
Max Act: 8.5964. Min Act: -0.1700
Data Index: 6672020 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5964. Min Range: -8.5964
Max Act: 8.2839. Min Act: -0.1700
Data Index: 7885640 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5964. Min Range: -8.5964
Max Act: 8.2839. Min Act: -0.1700
Data Index: 2663433 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5964. Min Range: -8.5964
Max Act: 8.1276. Min Act: -0.1700
Data Index: 3045990 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5964. Min Range: -8.5964
Max Act: 8.0339. Min Act: -0.1700
Data Index: 3832148 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.8151. Min Act: -0.1700
Data Index: 8470185 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.7839. Min Act: -0.1700
Data Index: 5600033 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.7526. Min Act: -0.1700
Data Index: 1710800 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.7214. Min Act: -0.1700
Data Index: 7833810 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.6901. Min Act: -0.1700
Data Index: 1510241 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.6901. Min Act: -0.1700
Data Index: 6295868 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.6589. Min Act: -0.1700
Data Index: 8191671 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.5964. Min Act: -0.1700
Data Index: 7249137 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.5964. Min Act: -0.1700
Data Index: 5928481 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.5651. Min Act: -0.1700
Data Index: 4400838 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.5339. Min Act: -0.1700
Data Index: 1702719 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.4401. Min Act: -0.1700
Data Index: 2379527 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.4714. Min Act: -0.1700
Data Index: 1535926 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.4401. Min Act: -0.1700
Data Index: 913663 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5964. Min Range: -8.5964
Max Act: 7.4089. Min Act: -0.1700
Data Index: 1153344 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19