Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.3547. Min Act: -0.1700
Data Index: 4714679 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.3547. Min Act: -0.1700
Data Index: 6654317 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.1984. Min Act: -0.1700
Data Index: 8589211 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.1359. Min Act: -0.1700
Data Index: 752301 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.1046. Min Act: -0.1700
Data Index: 4635384 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.1046. Min Act: -0.1700
Data Index: 6922366 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.1046. Min Act: -0.1700
Data Index: 8369040 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.0421. Min Act: -0.1700
Data Index: 570515 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9171. Min Act: -0.1700
Data Index: 7460151 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9483. Min Act: -0.1700
Data Index: 602635 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9483. Min Act: -0.1700
Data Index: 3461669 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9483. Min Act: -0.1700
Data Index: 4564420 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9171. Min Act: -0.1700
Data Index: 5076067 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9171. Min Act: -0.1700
Data Index: 2458857 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9171. Min Act: -0.1700
Data Index: 5629099 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9171. Min Act: -0.1700
Data Index: 2524020 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9171. Min Act: -0.1700
Data Index: 5572744 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.8858. Min Act: -0.1700
Data Index: 4121650 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.8858. Min Act: -0.1700
Data Index: 8344038 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.8858. Min Act: -0.1700
Data Index: 6397199 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19