Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1964. Min Range: -5.1964
Max Act: 5.1964. Min Act: -0.1700
Data Index: 295110 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1964. Min Range: -5.1964
Max Act: 5.1651. Min Act: -0.1700
Data Index: 3434334 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1964. Min Range: -5.1964
Max Act: 5.0714. Min Act: -0.1700
Data Index: 5747515 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1964. Min Range: -5.1964
Max Act: 5.0089. Min Act: -0.1700
Data Index: 3434325 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1964. Min Range: -5.1964
Max Act: 5.0089. Min Act: -0.1700
Data Index: 3434324 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.9464. Min Act: -0.1700
Data Index: 3434333 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.9464. Min Act: -0.1700
Data Index: 3850223 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.8839. Min Act: -0.1700
Data Index: 6568681 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.8526. Min Act: -0.1700
Data Index: 5747522 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.8526. Min Act: -0.1700
Data Index: 247260 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.8526. Min Act: -0.1700
Data Index: 8543853 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.8214. Min Act: -0.1700
Data Index: 3434336 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.8214. Min Act: -0.1700
Data Index: 5098985 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.7589. Min Act: -0.1700
Data Index: 5747533 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.7276. Min Act: -0.1700
Data Index: 5180977 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.7276. Min Act: -0.1700
Data Index: 4165775 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.7276. Min Act: -0.1700
Data Index: 5098978 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.7589. Min Act: -0.1700
Data Index: 8671810 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.6651. Min Act: -0.1700
Data Index: 4112238 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1964. Min Range: -5.1964
Max Act: 4.6964. Min Act: -0.1700
Data Index: 2454737 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19