Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1523 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0697. Min Range: -3.0697
Max Act: 3.0697. Min Act: -0.1700
Data Index: 2959726 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0697. Min Range: -3.0697
Max Act: 3.0381. Min Act: -0.1700
Data Index: 3039499 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0697. Min Range: -3.0697
Max Act: 3.0223. Min Act: -0.1700
Data Index: 536398 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.9749. Min Act: -0.1700
Data Index: 1595869 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.9433. Min Act: -0.1700
Data Index: 1190316 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8957. Min Act: -0.1700
Data Index: 2976805 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8640. Min Act: -0.1700
Data Index: 7197706 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8481. Min Act: -0.1700
Data Index: 6596141 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8481. Min Act: -0.1700
Data Index: 6050924 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8481. Min Act: -0.1700
Data Index: 3065462 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8322. Min Act: -0.1700
Data Index: 1487813 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8322. Min Act: -0.1700
Data Index: 3316946 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8163. Min Act: -0.1700
Data Index: 7144900 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8322. Min Act: -0.1700
Data Index: 6581389 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8322. Min Act: -0.1700
Data Index: 6076967 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8163. Min Act: -0.1700
Data Index: 1301456 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8163. Min Act: -0.1700
Data Index: 3875706 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8004. Min Act: -0.1700
Data Index: 1425009 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8004. Min Act: -0.1700
Data Index: 2538562 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0697. Min Range: -3.0697
Max Act: 2.8163. Min Act: -0.1700
Data Index: 1764759 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19