Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.9547. Min Act: -0.1700
Data Index: 6940259 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.8922. Min Act: -0.1700
Data Index: 6173776 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.8297. Min Act: -0.1700
Data Index: 8677585 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.7672. Min Act: -0.1700
Data Index: 3379151 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.7360. Min Act: -0.1700
Data Index: 3564086 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.7047. Min Act: -0.1700
Data Index: 8331 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.7047. Min Act: -0.1700
Data Index: 7766571 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.7047. Min Act: -0.1700
Data Index: 6837933 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.6422. Min Act: -0.1700
Data Index: 7604472 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.6110. Min Act: -0.1700
Data Index: 42337 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5797. Min Act: -0.1700
Data Index: 5439013 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5485. Min Act: -0.1700
Data Index: 2347862 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5797. Min Act: -0.1700
Data Index: 8297774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5797. Min Act: -0.1700
Data Index: 2198806 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5485. Min Act: -0.1700
Data Index: 893495 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5172. Min Act: -0.1700
Data Index: 381129 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5172. Min Act: -0.1700
Data Index: 5201814 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5172. Min Act: -0.1700
Data Index: 2535064 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5172. Min Act: -0.1700
Data Index: 7876328 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9547. Min Range: -5.9547
Max Act: 5.5172. Min Act: -0.1700
Data Index: 669150 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19